Breast cancer, a prevalent and diverse form of cancer, is characterized by unique clinicopathologic features. Accurate classification of its molecular subtype, essential for targeted treatment and improved survival rates, relies on testing molecular biomarkers such as estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki67 antigen. This study introduces an innovative two-stage machine learning pipeline for breast cancer PR molecular biomarker classification using whole slide immunohistochemistry images. Our approach consists of two specialized stages. In the first stage, a watershed algorithm segments the Cells from the input image. Morphological and statistical features extracted from these segments are then used by machine learning classifiers to distinguish between tumor and nontumor tissues [1] –[3]. The second stage focuses on the tumor tissues that were identified in the first stage, extracting texture and appearance features to classify them into positive or negative biomarker responses, again using machine learning classifiers [4], [5]. This method not only automates the classification of PR biomarkers in tumor regions but also generates a detailed image map for each cell in the Whole Slide Image (WSI). By doing so, it can determine whether the tissue represents tumor cells and whether the tumor tissue exhibits positive or negative PR status. The results show the ability of our machine learning-based approach to augment pathologists’ diagnostic capabilities, offering significant advancements in the automated classification of histopathological images.

Accurate early diagnosis is crucial in addressing Age-related Macular Degeneration (AMD), a chronic retinal disease that is a leading cause of blindness among the elderly. Medical imaging, particularly fundus imaging, is essential in facilitating timely detection and intervention. Due to the variability in image sizes within our dataset, this paper introduces the SABiT-MNet model, which effectively discriminates between healthy retinas, dry AMD, and wet AMD. The model integrates a novel scale-adaptive (SA) approach by combining an autoencoder with Big Transfer (BiT) as its backbone. Unlike traditional resizing methods, which often result in the loss of critical diagnostic information, the SA model dynamically adjusts to varying image sizes, preserving key retinal features essential for accurate diagnosis. The primary aim of this architecture is to retain crucial details in fundus images to ensure precise classification. In this study, 648 subjects were recruited through the Comparisons of AMD Treatments Trials study group, sponsored by the University of Pennsylvania. Experimental results demonstrate that the proposed SABiT-MNet model outperforms state-of-the-art approaches, including transformer-based models, achieving superior diagnostic accuracy. The model recorded performance metrics of 94% accuracy, 97% sensitivity, and 93.94% specificity. To further validate the robustness of the system, we tested it on the public ODiR dataset, where it achieved similarly promising results, confirming the effectiveness of our approach.

A novel diagnostic system is introduced for assessing the required level of respiratory support for COVID-19 patients. It bases its assessments on the correlation between detected COVID-19 lesions and the respiratory support levels administered to the patients. The correlation with computed tomography (CT) scans will focus on three respiratory support levels, including minimal support (Level 0), non-invasive support (Level 1, such as soft oxygen), and invasive support (Level 3, e.g., mechanical ventilation). The system initially outlines the pulmonary regions from CT scans, then identifies COVID-19 lesions within these segmented lung regions. Subsequently, three second-order texture features are extracted from the identified COVID-19 lesion regions to detect differences and abnormalities across varying severity levels in COVID-19 cases. To obtain the suitable level of respiratory support for each patient, a fusion mechanism based on backpropagation neural network is utilized to integrate the diagnosis of these three features, individually generated by the support vector machine (SVM) classifier. The system’s performance is evaluated on 307 COVID-19 patients using a hold-out validation approach. This evaluation included various metrics, such as sensitivity, specificity, F1-score, Cohen’s kappa, and accuracy, demonstrating impressive results. Specifi-cally, it achieved a score of 97.25%, 98.56%, 97.26%, 95.79%, and 97.25%, respectively. The results demonstrate the effectiveness of the integrated system, which uses various second-order features, in predicting respiratory support needs for COVID-19 patients, outperforming both its individual components and other machine learning-based classification systems.

This paper presents AFMUNet, an Adaptive Filter-Based Frequency Modulation U-Net for Optical Coherence Tomography Angiography (OCTA) segmentation. The model addresses the challenge of segmenting both small blood vessels and larger vascular structures, which exhibit significant variations in scale, contrast, and connectivity. To tackle these issues, AFMUNet achieves an image-sized receptive field while capturing global dependencies, enhancing performance across diverse vessel sizes. Specifically, it incorporates the Fast Fourier Transform (FFT) applied to feature maps across multiple scales of a UNet-like architecture. This component is crucial for identifying critical global frequency patterns, enabling the model to represent the intricate details of small vessels alongside larger ones. Simultaneously, a lightweight attention block is employed to learn adaptive frequency filters from the FFT-derived representations. This mechanism selectively emphasizes transferable frequency components essential for highlighting small and thin vessels while suppressing noise and less informative features that could detract from the segmentation of large vascular structures. Experimental evaluations demonstrate that AFMUNet outperforms state-of-the-art models, achieving mean Dice and mean Intersection over Union (IoU) scores of 91.69% and 84.65%, respectively. These results underscore its robustness and superior ability to accurately segment OCTA images, effectively addressing the dual challenge of capturing both fine-grained and coarse vascular details.

This paper introduces a novel framework, termed RAW (Region Attention-Weighted Network with Inter-Region Information Exchange), specifically developed for Age-related Macular Degeneration (AMD) grading using high-resolution input images. The framework begins with a High-Fidelity Detail Retention (HFDR) block, designed to preserve critical image details essential for accurate analysis. Furthermore, a lightweight network, inspired by ResNet, is incorporated to facilitate efficient feature extraction. This is augmented by a Region Attention-Weighted (RAW) block, which highlights significant regions while mitigating interference from less relevant areas. To ensure the effective propagation of crucial information for precise AMD grading, we developed the Inter-Region Information Exchange (IRIE) block. The efficacy of the proposed RAW framework was evaluated using a dataset comprising 864 Color Retinal Fundus (CRF) images, demonstrating outstanding performance compared to existing methods. It achieved a mean accuracy of 98.08%, a mean F1-score of 98.06%, and a mean Cohen’s Kappa of 97.42%. Statistical analysis further confirms the framework’s significant advantage, particularly in terms of F1-score, underscoring its robustness and exceptional capability for AMD grading.

Breast cancer is a highly complex disease that requires precise molecular subtyping to guide tailored treatment strategies. In this study, we employed a marker-based watershed segmentation technique on a breast cancer dataset, enabling the extraction of essential morphometric parameters. These included area, perimeter, circularity, maximal and minimal calipers, and eccentricity, along with hematoxylin and diaminobenzidine (DAB) staining characteristics for individual cells, nuclei, and cytoplasm. We utilized Support Vector Machine (SVM) and Random Forest (RF) models to classify molecular biomarker response scores to identify their molecular subtypes, leveraging these extracted features as discriminative factors. The dataset comprised whole-slide images (WSI) annotated with Progestin Receptors (PR) molecular biomarker response scores, categorizing cell regions into different classes: "other", "tumor: negative", "tumor: +1", "tumor: +2", and "tumor: +3". These detailed annotations enhanced the AI-driven classification of breast cancer molecular biomarkers response score detection on cell level. Performance evaluation of the proposed framework demonstrated substantial classification accuracy, with SVM achieving over 93% in precision, recall, F1-score, and overall accuracy, while RF exceeded 96% across these metrics. The study's findings highlight the efficacy of integrating marker-based watershed segmentation with morphometric and staining analysis for precise breast cancer molecular biomarkers response score classification. This approach provides deeper insights into tumor heterogeneity, reinforcing the importance of incorporating morphometric and staining parameters in molecular biomarkers response score classification and hence improved personalized treatment and prognosis.

This paper introduces CrossDR, a novel approach unifying 2D and 3D feature representations through a context-aware cross-attention mechanism for diabetic retinopathy (DR) classification in 3D Optical Coherence Tomography (OCT) scans. The model uncovers critical diagnostic cues embedded in 3D-OCT images, which offer rich information for DR detection. The framework comprises three core components: the Lightweight Attention (LA) block, a CNN-based encoder, and the Context-Aware Cross-Attention (CA)2block. The LA block highlights volume-specific features that are crucial for DR diagnosis. It achieves this by applying a series of 1×1 convolutions followed by softmax operations, enabling the extraction of spatially informative DR-specific features. Meanwhile, the CNN-based encoder extracts high-level semantic features from the 3D-OCT slices, offering a robust representation of retinal structures. The (CA)2block further boosts the model’s performance by dynamically capturing and reweighting feature dependencies. This block models relationships between feature maps at different abstraction levels, improving the discriminative power of the extracted features. By integrating these refined features through the (CA)2block, the model achieves accurate DR classification. The CrossDR framework was evaluated on 481 volumetric OCT images, outperforming existing state-of-the-art methods with an accuracy of 94%. Multiple experiments and ablation studies were conducted to assess our model’s performance.

This study proposes a novel deep learning-based automatic segmentation system for accurately delineating pulmonary regions in 3D computed tomography (CT) scans. First, a modified local binary pattern, called cylinder binary pattern (CBP), is introduced, which utilizes concentric cylinders at different radii, to effectively capture intricate textural details at multiple levels. Then, a 3D encoder-decoder deep learning-based network, called VX-Net, is proposed specifically to accurately segment pulmonary regions within 3D CT scans. This network incorporates the hierarchical transformers into its encoder architecture to significantly improve feature extraction process. These transformers replicate Transformer model by integrating 3D convolutions with both larger and smaller kernels. While this network is used for segmenting pulmonary regions, it can also be adapted for various other segmentation tasks. The proposed system is evaluated on 3D CT scans of 26 patients with three different severity levels of COVID-19, using four distinct metrics. These include Dice similarity coefficient (DSC), overlap coefficient, Hausdorff distance (HD), and absolute volume difference (AVD). The proposed system shows remarkable performance, achieving scores of 97.63±0.98%, 95.38±1.86%, 1.99±1.9, and 3.01±1.15, respectively. When compared to various state-of-the-art segmentation methods, the proposed segmentation system showcases its ability to accurately segment both normal and pathological pulmonary regions.

We propose a novel AI-based system for breast cancer (BCa) assessment to predict response to neoadjuvant chemotherapy (NAC) into one of three responses: Partial Response (PR), Complete Response (CR), and Stationary Disease (SD), providing a full insight for medical experts about treatment regimens. The proposed AI-based system integrates machine learning (ML) and deep learning (DL) approaches to incorporate both global and local markers for more accurate prediction. The ML approach, based on a decision tree model, learns patterns from global markers extracted through pathology assessments to determine molecular subtypes. This analysis incorporates four standard tests: ER, PR, HER2, and Ki-67. Additionally, it integrates global radiomics descriptors, including tumor morphology, lesion count, and radiologist assessments for axillary nodes (benign vs. suspicious). In addition to assessing global markers, we employed a pre-trained Vision Transformer (ViT-b16) with a multihead adaptive self-attention mechanism to extract local markers from the Region of Interest (ROI) around the breast tumor. This approach eliminates the need for segmentation, which could impact the accuracy of the local AI model’s prediction. The outputs of both models are fused using a GradientBoosting algorithm to predict the response to NAC. The proposed system was tested on 736 2D images along with their corresponding radiomics and pathological markers (CR = 156, PR = 353, and SD = 227). The developed AI-based system achieved an accuracy of 98.91%. Explainability was enabled through heatmaps which visually highlight areas with high attention for decision-making. These results demonstrate promising potential for AI-based early assessment in BCa management.

Computerized diagnostic systems have come a long way in terms of providing credible and speedy results in the diagnosis of lung cancer, which has become one of the leading causes of death worldwide in recent years. This progress is particularly true with the advancements in models based on deep convolutional neural networks (CNNs) using computed tomography (CT) images. However, the decision-making processes of such models are less than exactly interpretable, as they are considered black boxes. This makes physicians reluctant to trust and use them.The aim of this paper is to compare several transfer models that were pre-trained on the ImageNet dataset and apply them to lung cancer diagnosis, evaluating their generalizability and robustness. This comparative study implements a number of models including MobileNetV2, EfficientNetV2-L, EfficientNet-B7, DenseNet201, VGG19, VGG16, ResNet50, Xception, NasNetLarge, and InceptionV3. The models were trained on four distinct datasets to evaluate data diversity and heterogeneity. The models’ generalization capabilities were assessed using two separate datasets: IQ-OTH/NCCD and the LDCT dataset. To enhance the models explainability and trustworthiness, the Local Interpretable Model-Agnostic Explanations (LIME) method was utilized. Among the tested models, MobileNetV2 and ResNet50 demonstrated the highest performance and stability. MobileNetV2 achieved an accuracy of 99.28%, with false positive and false negative rates of 1.23% and 0%, respectively. ResNet50 achieved an accuracy of 99.38%, with false positive and false negative rates of 0% and 1.23%, respectively.

COVID-19, a respiratory illness caused by SARS-CoV-2, has brought attention to a common symptom: loss of smell and taste. Anosmia, a prevalent symptom of COVID-19, varies in severity from mild to severe, necessitating accurate diagnostic tools. The study proposes a novel framework for predicting COVID-19 anosmia severity utilizing YOLOv8 for classification and EigenCAM for interpretability. YOLOv8, optimized for object detection, is adapted for classification tasks using advanced architectural enhancements and mosaic augmentation. EigenCAM provides interpretability by highlighting image regions crucial for predictions, aiding clinical decision-making. Evaluation across multiple YOLOv8 model sizes using DTI and FLAIR modalities reveals robust performance, with the Large model excelling in DTI and the Nano model in FLAIR. Compared to our previous work, the framework significantly enhances accuracy and interpretability in predicting anosmia severity, marking a substantial advancement in medical image analysis. This study underscores the potential of deep learning for precise and interpretable medical diagnostics, offering insights into anosmia severity prediction.

This paper introduces a novel framework for renal segmentation of kidney transplant patients suspected of renal rejection. The framework applies image processing techniques for texture analysis utilizing a modified Pix 2 Pix GAN model to capture the varied kidney shapes in the dataset of 36 subject volumes acquired using BOLD MRI scans. For this problem, we built a framework that analyzes the kidney texture based on four steps: (i) calculate the average CDF for each case to map CDF values to their corresponding intensities for contrast enhancement (ii) extract the region of interest for the kidney to focus on the kidney structure, (iii) calculate the probability maps using the histograms of the contours for the kidney and non-kidney regions, (iv) Create a common-layer across the dataset using the masks by calculating the average of the pixel values of the images to accommodate the shared information within the mask images. Finally, stack the three layers to have the RGB channels contain relevant information about the renal dataset as input for the modified GAN model. The proposed framework achieved an average accuracy and Dice Similarity Coefficient: $90.3 \%$, and $83.1 \%$, respectively. The framework’s primary results underscore its efficiency in providing segmentation for renal diagnosis.

This paper introduces an automatic segmentation system designed for precise outlining of the pulmonary area within 3D computed tomography (CT) scans, utilizing a combination of unsupervised and supervised models. Initially, an unsupervised model is utilized to depict the empirical distribution of Hounsfield units in both lung and chest regions within the 3D CT volume. This representation takes the form of a probability model based on a linear combination of Gaussians, determined through a modified expectation maximization (EM) algorithm. Subsequently, the LCG-based segmentation is refined by modeling it with a spatial probabilistic model using a 3D Markov Gibbs random field (MGRF) with analytically estimated potentials. Finally, a supervised deep learning model is introduced and integrated with the proposed unsupervised model to achieve superior segmentation results. The efficacy of the proposed method is assessed using 3D chest scans from 29 patients confirmed with varying degrees of severity in COVID-19. This evaluation employs four distinct metrics: Dice similarity coefficient (DSC), overlap coefficient, Hausdorff distance (HD), and absolute volume difference (AVD), achieving remarkable results of $97.35_{ \pm 1.51} \%, 94.89_{ \pm 2.80} \%$, $3.39_{ \pm 1.61}$, and $2.70_{ \pm 2.88}$, respectively. When compared to four state-of-the-art deep learning-based methods, the proposed system demonstrated outstanding performance in segmenting pathological lung tissues, highlighting its potential and efficacy.

Hepatocellular carcinoma (HCC), – the main form of liver cancer –, is the second global leading cause of cancer-related mortality. LI-RADS is considered the worldwide non-invasive standard method for imaging interpretation and reporting in patients with HCC eliminating the need for biopsy. However, it might be prone to interpretation subjectivity. Therefore, we develop an objective non-invasive AI-based grading system for HCC for appropriate etiology treatment plans. The developed system integrates potential image-based markers that represent the tumor’s morphology, functionality, and appearance/texture with the associated clinical biomarkers. The study encompasses 117 patients diagnosed with HCC and was divided into three different groups (group 1: benign low-grade (LR 1,2), N = 41; group 2: malignant high-grade (LR 4,5), N = 39; and group 3: malignant not HCC (LR-M), N = 37). Diffusion-weighted magnetic resonance imaging (DWI) was acquired for imaging-based markers identification. The developed grading system pipeline includes: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of appearance/textural markers using a novel rotation invariant circular binary pattern model, iii) calculation of the functional markers by constructing the representative cumulative distribution functions of the estimated apparent diffusion coefficients, and iv) integrating the aforementioned imaging-based markers with the associated clinical biomarkers, known as Alpha-fetoprotein. The integrated markers were optimized to train and test multiple machine learning (ML) classifiers and a hyper-tuned custom CNN. On a randomly stratified train (80%) test (20%) split scheme, the developed obtained an overall accuracy of 88% in differentiating between the three groups using the integrated markers along with the CatBoost classifier, surpassing the diagnostic performance of individual marker sets, other ML classifiers, and the CNN as well. The obtained results demonstrate the feasibility of the developed system as a novel tool for non-invasive and objective HCC grading.

We propose an automated, explainable artificial intelligence (xAI) system for age-related macular degeneration (AMD) diagnosis. Mimicking the physician's perceptions, the proposed xAI system is capable of deriving clinically meaningful features from optical coherence tomography (OCT) B-scan images to differentiate between a normal retina, different grades of AMD (early, intermediate, geographic atrophy (GA), inactive wet or active neovascular disease [exudative or wet AMD]), and non-AMD diseases. Particularly, we extract retinal OCT-based clinical imaging markers that are correlated with the progression of AMD, which include: (i) subretinal tissue, sub-retinal pigment epithelial tissue, intraretinal fluid, subretinal fluid, and choroidal hypertransmission detection using a DeepLabV3+ network; (ii) detection of merged retina layers using a novel convolutional neural network model; (iii) drusen detection based on 2D curvature analysis; (iv) estimation of retinal layers' thickness, and first-order and higher-order reflectivity features. Those clinical features are used to grade a retinal OCT in a hierarchical decision tree process. The first step looks for severe disruption of retinal layers' indicative of advanced AMD. These cases are analyzed further to diagnose GA, inactive wet AMD, active wet AMD, and non-AMD diseases. Less severe cases are analyzed using a different pipeline to identify OCT with AMD-specific pathology, which is graded as intermediate-stage or early-stage AMD. The remainder is classified as either being a normal retina or having other non-AMD pathology. The proposed system in the multi-way classification task, evaluated on 1285 OCT images, achieved 90.82% accuracy. These promising results demonstrated the capability to automatically distinguish between normal eyes and all AMD grades in addition to non-AMD diseases.

Breast cancer is a prevalent and diverse type of cancer that exhibits unique clinicopathologic characteristics, making the correct identification of its subtype critical to providing targeted treatment and increasing survival rates. This identification process involves testing for the presence of four key molecular biomarkers, namely estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and antigen Ki67. For accurate diagnosis ,the expertise of a pathologist and immunohistochemistry is required. To overcome this diagnostic challenge, we present a novel approach based on a deep learning pipeline for automated classification. Our approach can detect tumor and non-tumoral regions of the HER2 biomarker. Our deep learning framework comprises a Dense Convolutional Network (DenseNet), which process whole slide images (WSIs) of breast tissues, dividing them into patches for input into the network. Moreover, our approach provides both patchwise and pixelwise classification and analyzes ten WSIs of breast cancer histology. Our proposed approach generates an image map that classifies slide images on the pixel-level, detecting the status of hormone HER2 receptor as either positive or negative. The obtained results show that our deep learning-based approach has the potential to enhance the pathologist’s capabilities in diagnosing histopathological images with automated classification.

Retinal disorders diagnosis is of immense importance for appropriate treatment, i.e., accurate personalized medicine. In this work, a multi-resolutional feature ensemble approach is developed for retinal image classification using optical coherence tomography (OCT) images. Particularly, feature-rich pipeline using pyramidal architecture is designed to extract features from multi-scale inputs using partially-connected networks (PCNet). In addition, higher-order reflectivity features are extracted from the input images and are fused with pyramidal features for classification. The advantage of the hierarchical PCNet structure is that it allowed our system to extract multi-scale information to help in such task, all-at-once classification of the normal and abnormal retina. Namely, the larger input sizes give more global information, while the small inputs focus on local details. Evaluation on public OCT data set of four classes (normal, diabetic macular edema (DME), choroidal neovascularization (CNV), and drusen) and comparison against recent networks demonstrates not only the advantages of the proposed architecture’s ability to produce feature-rich classification, but also highlights tangible advantages, such as network parameter reduction, enhanced feature learning and information flow, while reducing the risk of over fitting.

Prostate cancer (PCa) is a widespread type of cancer that leads to numerous fatalities and a high financial cost. The chance of survival for PCa patients increases when the disease is detected at an early stage. This study discusses the development of a non-invasive computer-aided diagnosis (CAD) system that utilizes intravoxel incoherent motion (IVIM) parameters to detect and diagnose prostate cancer. The study focuses on IVIM, which can separate the diffusion of water molecules in capillaries from the molecular diffusion outside of the vessels, and its diagnostic efficacy in the central and peripheral zones of prostate cancer. The study proposes a two-step segmentation approach for tumor detection, starting with the precise localization of the prostate gland using a robust level-sets technique and then using an Attention U-Net to extract the tumor-containing region of interest (ROI) from the segmented image. The study evaluates the performance of the CAD system, the best classifier and IVIM parameters for differentiation, and the diagnostic value of IVIM parameters compared to ADC. The results of this study contribute to the development of non-invasive methods for early prostate cancer detection and diagnosis. The IVIM (CZ + PZ) parameters that utilized the extra trees classifier (ETC) and were implemented without principal component analysis (PCA) and standardization scaling achieved the best metrics. They produced an accuracy of 84.62%, a balanced accuracy of 82.58%, a precision of 80%, a specificity of 67.86%, a sensitivity of 97.30%, an F1-score of 87.12%, an IoU of 78.26%, a ROC of 83.88%, and a weighted sum metric (WSM) of 82.79%.

A novel unsupervised-based segmentation method is introduced to accurately delineate the lung region in 3D CT images based on appearance and geometric models. First, a probabilistic model that utilized a linear combination of Gaussian (LCG) tuned by a modified expectation maximization (EM) algorithm, is employed to model the density distribution of 3D CT chest volume. Subsequently, the initial labeling of the 3D CT chest volume is mapped to a probability distribution based on a 3D Markov Gibbs random field (MGRF) for refining. Finally, a geometric model is employed to refine the proposed segmentation by interpolating/connecting two points on its boundary with high curvature. The effectiveness of the proposed approach on 3D computed tomography (CT) chest scans of 26 patients diagnosed with different severity of coronavirus disease 2019 (COVID-19) is evaluated using four different metrics: overlap coefficient, Dice similarity coefficient (DSC), absolute lung volume difference (ALVD), and 95th-percentile bidirectional Hausdorff distance (95thHD). The proposed method achieved 94.89%±2.39%, 97.36%±1.27%, 1.79±1.89, and 4.75±2.3, respectively. Compared to three state-of-the-art methods based on deep learning approaches, the proposed method achieved superior performance in segmenting pathological lung tissues, demonstrating the promising of the proposed segmentation system.

Industrial health monitoring in factories is essential for quality assurance, energy and cost reduction, and health and safety. In aluminum factories, anode furnace pits’ flue walls deform over time due to cyclic heating and cooling. They are inspected and classified using manually acquired measurements in a process that takes several hours and is done under high temperatures using specialized equipment. We propose an end-to-end AI-powered system for automated inspection using drones. We fly a drone carrying color and depth cameras to film and navigate a 50-pit furnace floor autonomously in a GPS-denied environment. We then mosaic the recorded videos to produce color and depth mosaics using frame-to-frame motion parameters estimated using the color videos and applied to both. We finish the mosaics using depth-to-color mosaic registration based on maximizing mutual information on gradients. We extract pit images from the mosaics using a YOLOv5 object detection initially trained using a physical floor model with a proposed data augmentation scheme and then fine-tuned for the on-site environment. We achieve a mean average precision of 94.7%. Once pit images are detected and initially classified, we propose a dual-stage segmentation algorithm using the Hough transform and a semantic segmentation network trained using probabilistic feature images with a precision of 96.67%. Segmented pits with depth information allow us to produce 3D models of pits to aid in temporal monitoring and diagnosis confirmation. Our system is cost-effective and reduces inspection downtime by 87%, eliminating the need for human intervention.

In this study, we propose a Computer-Aided Diagnostic (CAD) system to diagnose and understand autism spectrum disorder (ASD) using structural MRI (sMRI). Starting with identifying morphological anomalies within the cortical regions of ASD subjects. Every cortical feature receives a score corresponding to their contribution in diagnosing a subject to be ASD or typically developed (TD). Scores are determined by hyper-optimized machine learning (ML) classifiers. An early personalized diagnosis of ASD becomes possible by the proposed CAD system. The proposed framework implements multiple stages including cerebral cortex extraction from structure MRI (sMRI). Moreover, the proposed framework identify the altered brain regions. We can summarize this framework in the following procedures: i) Cerebral cortex segmentation, ii) Parcellation of the cortex to Desikan-Killiany (DK) atlas; iii) Annotating brain regions which are associated with ASD; iv) Blocking for the confounding effect of both age and sex; v) Tailoring ASD neuro-atlases; vi) Classifying ASD using neural networks (NN). We uti-lized Autism Brain Imaging Data Exchange (ABIDE I) dataset to test the proposed framework. The proposed achieved a balanced accuracy score of 97% ± 2%. In this study, we demonstrate the ability to describe specific developmental patterns of the brain in autism using tailored neuro-atlases, as well as, developing an objective CAD system using morphological features extracted from sMRI scans.

Gliomas are the most common type of primary brain tumors and one of the highest causes of mortality worldwide. Glioma grading is of immense importance to administer proper treatment plans. In this paper, we develop a comprehensive noninvasive multimodal magnetic resonance (MR)-based computeraided diagnostic (CAD) system that has the ability to differentiate between high grade gliomas (HGG) and low grade gliomas (LGG). The proposed glioma grading (GG-CAD) system utilizes three different MR imaging modalities, namely; contrast-enhanced T1-MR, T2-MR known as fluid-attenuated inversion-recovery (FLAIR), and diffusion-weighted (DW-MR) to extract the following imaging features: (i) morphological features based on constructing the histogram of oriented gradients (HOG) and estimating the glioma volume, (ii) first and second orders textural features by constructing histogram, gray-level run length matrix (GLRLM), gray-level co-occurrence matrix (GLCM), and (iii) functional features by estimating voxel-wise apparent diffusion coefficients (ADC) and wash-in slope. These features are then integrated together and processed using a multi-layer perceptron artificial neural networks (MLP-ANN) classification model towards getting the final diagnosis of a glioma as HGG or LGG. The GG-CAD system was evaluated on a total of 82 gliomas (HGG = 42 and LGG = 40) using a k-fold cross-validation approach (k = 82, 10, and 5). The GG-CAD achieved 98.8%±1.0% accuracy, 99.2%±1.1% sensitivity, 98.3%±1.2% specificity, and 0.99%±0.01% F1score at k = 82 and an outstanding diagnostic performance at k = 10 and 5. The obtained diagnostic results hold promise of the developed GG-CAD system as a non-invasive diagnostic tool.

Prostate cancer (PC) is the most common cancer, a significant cause of morbidity, and is the second vital cancer that causes death in the US. Early PC detection is one of the major factors in decreasing mortality. We introduce a deep learning (DL) system for automated Gleason system grading (Gleason pattern (GP) and Gleason score (GS)) and grade groups (GG) using whole slide images (WSIs) of the digitized prostate biopsy specimens (PBSs). The DL is a pyramidal convolution neural network (CNN) approach consisting of progressively larger patch-sized shallow CNN to provide hierarchical information features. We used three patches sizes 100×100 (small), 150×150 (median), and 200×200 (large) pixels, so the pyramidal CNN affords us varying contextual features. The small patches give more local information, while the large patches provide global features. The patch-wise classification yields five probabilities representing the GP types from 1 to 5 at each pyramidal level. Then, we get the average for those three levels. We used three metrics to evaluate the GP classification diagnostic: recall, accuracy, and precision. The classification accuracy for the CNNL(large patches) is 0.77, the best among the three CNNs. The GG results are between 50% to 75% for recall. GG’s results are highlighted in our DL systems by comparing them with the current work.

The most critical steps to improve the clinical management of the lung cancer are the early detection and the accurate diagnosis. In this study, an automated system for lung cancer diagnosis from one computed tomography (CT) scan is developed to distinguish between malignant and benign nodules. This system utilizes two different kinds of features to describe the lung nodules. These features indicate the nodule’s preceding growth rate, which is considered the major point in pulmonary nodule diagnosis. Analytical Local Binary Pattern is implemented to characterize the pulmonary nodule texture. Special functions called spherical harmonics are used to characterize the nodule surface. Finally, a stacked autoencoder is utilized to reduce the dimensionality of the modeled features values and to eliminate the noise in the data followed by a probability-based linear classifier to diagnose the nodule. The proposed system is tested using Lung Image Database Consortium (LIDC) database. The effectiveness of the presented framework is confirmed where the system accuracy, sensitivity, specificity, and area under the ROC curve of 93.79%, 94.36%, 92.80%, and 0.9764 respectively are achieved.

Early detection and diagnosis of thyroid nodules are very important to rescue patients before the cancer spreads all over the patient’s body. A computer-aided diagnosis (CAD) system is proposed to detect the malignancy of thyroid nodules using magnetic resonance imaging (MRI) scans. This system extracts three descriptive features from T2-weighted (T2) MRI. These features are 1st-order reflectivity, 2nd-order reflectivity, and spherical harmonic. The 1st-order reflectivity is represented by sufficient statistics, (i.e. CDF percentiles), extracted from the cumulative distribution function (CDF) generated from it. After-ward, these features are fed to a neural network (NN) individually for diagnosis. Then, the classification outputs for these networks are fused using another NN for final diagnosis. The developed system is trained and tested using leave-one-subject-out (LOSO) cross-validation technique on MRI scans from 63 patients. The proposed fusion system shows incredible improvements in diagnostic accuracy, compared with other machine learning approach and a well-know pretrained deep learning network as well as individual feature classification. The overall sensitivity, specificity, F1-score, and accuracy of the proposed system are 91.3%, 95%, 91.3%, and 93.65%, respectively. The reported results, based on the fusion of reflectivity features as well as morphological feature, show the promise of the developed system in differentiating between benign and malignant thyroid nodules.

Prostate Cancer (PC) has been shown to become an epidemic among men in the world. Early detection of PC is essential for treatment. Biopsies are often done to determine the Gleason score of PC which helps to predict the aggressiveness of PC. As biopsies may cause harm especially for old people, machine learning can be used to predict the Gleason grade of PC from clinical biomarkers that are typically structured in a table. In this paper, we present a comparative study of various machine learning methods to detect the Gleason grade of PC from tabular data. We also investigate the performance of advanced deep learning architectures specialized to deal with tabular data, such as TabNet, for this purpose. Moreover, we propose to build an ensemble of the best performing classifiers to grade PC with a promising performance.

SARS-CoV-2 has infected over ∼165 million people worldwide causing Acute Respiratory Distress Syndrome (ARDS) and has killed ∼3.4 million people. Artificial Intelligence (AI) has shown to benefit in the biomedical image such as X-ray/Computed Tomography in diagnosis of ARDS, but there are limited AI-based systematic reviews (aiSR). The purpose of this study is to understand the Risk-of-Bias (RoB) in a non-randomized AI trial for handling ARDS using novel AtheroPoint-AI-Bias (AP(ai)Bias). Our hypothesis for acceptance of a study to be in low RoB must have a mean score of 80% in a study. Using the PRISMA model, 42 best AI studies were analyzed to understand the RoB. Using the AP(ai)Bias paradigm, the top 19 studies were then chosen using the raw-cutoff of 1.9. This was obtained using the intersection of the cumulative plot of "mean score vs. study" and score distribution. Finally, these studies were benchmarked against ROBINS-I and PROBAST paradigm. Our observation showed that AP(ai)Bias, ROBINS-I, and PROBAST had only 32%, 16%, and 26% studies, respectively in low-moderate RoB (cutoff>2.5), however none of them met the RoB hypothesis. Further, the aiSR analysis recommends six primary and six secondary recommendations for the non-randomized AI for ARDS. The primary recommendations for improvement in AI-based ARDS design inclusive of (i) comorbidity, (ii) inter-and intra-observer variability studies, (iii) large data size, (iv) clinical validation, (v) granularity of COVID-19 risk, and (vi) cross-modality scientific validation. The AI is an important component for diagnosis of ARDS and the recommendations must be followed to lower the RoB.

Kidney segmentation from Dynamic Contrast Enhanced Magnetic Resonance Images (DCE-MRI) is a fundamental step for the early detection of transplanted kidney function. This paper presents an accurate and automatic DCE-MRI kidney segmentation method which combines fuzzy c-means (FCM) algorithm and geometric deformable model (level set) method. In order to precisely extract the kidney from its background, the evolution of the level set contour in the proposed method is controlled by the fuzzy memberships of the pixels and both population-based and patient-specific shape model. The FCM algorithm is used to initially divide the input image into kidney and background clusters. The obtained fuzzy clustering membership is used to define the initial contour of the level set method. For segmenting the kidney of a specific patient, a number of high contrast time-point images are segmented constraining the evolution of the level set contour by the population-based shape model constructed from different subjects. As more images are segmented, the patient-specific shape model is built from the obtained segmentation results and gradually used to guide the evolution of the level set contour. The performance of the proposed method is evaluated on 40 subjects. Experimental results demonstrate the efficiency, consistency, and accuracy of the proposed method especially for low contrast images.

One thing that assists in automatic environmental monitoring is leaf segmentation. By segmenting a leaf, image-based leaf health assessment can be performed which is crucial in maintaining the effectiveness of the environmental balance. This paper presents a technique that serves an accurate framework for diseased leaf segmentation from Coloured imaged. In other words, this method works to use information generated from RGB images that we have stored in our data base to represent the current input image. To achieve such technique, four main steps were constructed: 1) Using contrast variations to characterize the region of interest (ROI) of a given leaf which enhances the accuracy of the segmentation using minimal time. 2) using linear combination of discrete Gaussians (LCDG) to represent the visual appearance of the input image and to assume the marginal probability distributions of the three regions of interest classes. 3) Using information generated from RGB images that we have stored in our data base to calculate the probabilities of the three classes on a pixel basis in step two. 4) Lastly, clarifying the labels with Gauss-Markov random field model (GGMRF) to maintain the continuity. After all these steps, the experimental validation promised high accuracy.

Hypertension is one of the severest and most common diseases nowadays. It is considered one of the leading contributors to death worldwide. Specialists tend to diagnose hypertension taking into consideration both systolic and diastolic blood pressure (BP) measurements. However, some clinical hypothesis states that under 50 years of age, diastolic may be slightly more predictive of adverse events, while above that age, systolic may be more predictive. The question is should we give more value to systolic BP or diastolic BP when diagnosing diseases such as hypertension? Three different experiments were conducted in this study using magnetic resonance angiography (MRA) data to investigate this question. In each of these experiments, the following methodology was followed: 1) preprocess MRA data to remove noise, bias, or inhomogeneities, 2) segment the cerebral vasculature for each subject using a CNN-based approach, 3) extract vascular features that represent cerebral alterations that precede and accompany the development of hypertension, and 4) finally build feature vectors and classify data into either normotensives or hypertensives based on the cerebral alterations and the blood pressure measurements. The first experiment was conducted on original data set of 342 subjects. While the second and third experiments enlarged the original data set by generating more synthetic samples to make original data set large enough and balanced. Experimental results showed that systolic blood pressure might be more predictive than diastolic blood pressure in diagnosing hypertension with a classification accuracy of 89.3%.

A precise computerized lung nodule diagnosis framework is very important for helping radiologists to diagnose lung nodules at an early stage. In this manuscript, a novel system for pulmonary nodule diagnosis, utilizing features extracted from single computed tomography (CT) scans, is proposed. This system combines robust descriptors for both texture and contour features to give a prediction of the nodule's growth rate, which is the standard clinical information for pulmonary nodules diagnosis. Spherical Sector Isosurfaces Histogram of Oriented Gradient is developed to describe the nodule's texture, taking spatial information into account. A Multi-views Peripheral Sum Curvature Scale Space is used to demonstrate the nodule's contour complexity. Finally, the two modeled features are augmented together utilizing a deep neural network to diagnose the nodules malignancy. For the validation purpose, the proposed system utilized 727 nodules from the Lung Image Database Consortium. The proposed system classification accuracy was 94.50%.

Recently, studies for non-invasive renal transplant evaluation have been explored to control allograft rejection. In this paper, a computer-aided diagnostic system has been developed to accommodate with an early-stage renal transplant status assessment, called RT-CAD. Our model of this system integrated multiple sources for a more accurate diagnosis: two image-based sources and two clinical-based sources. The image-based sources included apparent diffusion coefficients (ADCs) and the amount of deoxygenated hemoglobin (R2*). More specifically, these ADCs were extracted from 47 diffusion weighted magnetic resonance imaging (DW-MRI) scans at 11 different b-values (b0, b50, b100, ..., b1000 s/mm2), while the R2* values were extracted from 30 blood oxygen leveldependent MRI (BOLD-MRI) scans at 5 different echo times (2ms,7ms, 12ms, 17ms, and 22ms). The clinical sources included serum creatinine (SCr) and creatinine clearance (CrCl). First, the kidney was segmented through the RT-CAD system using a geometric deformable model called a level-set method. Second, both ADCs and R2* were estimated for common patients (N=30) and then were integrated with the corresponding SCr and CrCl. Last, these integrated biomarkers were considered the discriminatory features to be used as trainers and testers for future deep learning-based classifiers such as stacked auto-encoders (SAEs). We used a k-fold cross-validation criteria to evaluate the RT-CAD system diagnostic performance, which achieved the following scores: 93.3%, 90.0%, and 95.0% in terms of accuracy, sensitivity, and specificity in differentiating between acute renal rejection (AR) and non-rejection (NR). The reliability and completeness of the RT-CAD system was further accepted by the area under the curve score of 0.92. The conclusions ensured that the presented RT-CAD system has a high reliability to diagnose the status of the renal transplant in a non-invasive way.

Analyzing cerebrovascular changes using Time-of-Flight Magnetic Resonance Angiography (ToF-MRA) images can detect the presence of serious diseases and track their progress, e.g., hypertension. Such analysis requires accurate segmentation of the vasculature from the surroundings, which motivated us to propose a fully automated cerebral vasculature segmentation approach based on extracting both prior and current appearance features that capture the appearance of macro and micro-vessels. The appearance prior is modeled with a novel translation and rotation invariant Markov-Gibbs Random Field (MGRF) of voxel intensities with pairwise interaction analytically identified from a set of training data sets, while the current appearance is represented with a marginal probability distribution of voxel intensities by using a Linear Combination of Discrete Gaussians (LCDG) whose parameters are estimated by a modified Expectation-Maximization (EM) algorithm. The proposed approach was validated on 190 data sets using three metrics, which revealed high accuracy compared to existing approaches.

Early assessment of liver cancer patients with hepatocellular carcinoma (HCC) is of immense importance to provide the proper treatment plan. In this paper, we developed a two-stage classification computer-aided diagnostic (CAD) system that has the ability to detect and grade the liver observations from multiphase contrast enhanced magnetic resonance imaging (CE-MRI). The proposed approach consists of three main steps. First, a pre-processing is applied to the CE-MRI scans to delineate the tumor lesions that will be used as a region of interest (ROI) across the four different phases of the CE-MRI, (namely, the pre-contrast, late-arterial, portal-venous, and delayed-contrast). Second, a group of three features are modeled to provide a quantitative discrimination between the tumor lesions, namely: (i) the tumor appearance that is modeled using a set of texture features, (namely; the first-order histogram features, second-order gray-level co-occurrence matrix (GLCM) features, and second-order gray-level run-length matrix (GLRLM) features), to capture any discrimination that may appear in the lesion texture; (ii) the spherical harmonics (SH) based shape features that have the ability to describe the shape complexity of the liver tumors; and (iii) the functional features that are based on the calculation of the wash-in/wash-out slopes to evaluate the intensity changes across different phases. Finally, the aforementioned individual features were integrated together to obtain the combined features to be fed to a machine learning classifier towards getting the final diagnostic decision. The proposed CAD system was tested using hepatic observations obtained from 85 participating patients, 34 patients with benign tumors (LR-1 = 17 and LR-2 = 17), 34 patients with intermediate tumors (LR-3) and 34 with malignant tumors (LR-4 = 17 and LR-5 = 17). Using a random forests classifier with a leave-one-subject-out (LOSO) cross-validation, the developed CAD system achieved an 87.1% accuracy in distinguishing malignant, intermediate and benign tumors (i.e. First stage classification). Using the same classifier and validation, the LR-1 lesions were classified from LR-2 benign lesions with 91.2% accuracy, while 85.3% accuracy was achieved differentiating between LR-4 and LR-5 malignant tumors. The classification performance was then evaluated using k-fold (10 and 5-fold) cross-validation approaches to examine the robustness of the system. The obtained results hold a promise of the proposed framework to be reliably used as a noninvasive diagnostic tool for the early detection and grading of liver cancer tumors.

Diabetic Retinopathy (DR) is one of the leading causes of blindness in working age population worldwide. DR is caused by high blood sugar levels (diabetes), which damages retinal blood vessels and leads to vision loss. The diagnosis of DR requires manual measurements and visual assessment of the changes that happen in the retina, which is highly complex task. Thus, there is an unmet clinical need for a non-invasive, and objective diagnostic system that can improve the accuracy of early diagnosis of DR. In this paper, we develop and validate a computer-aided diagnostic (CAD) system for highly accurate, early diagnosis of DR. The proposed system use a 3D convolutional neural network (CNN) to segment blood vessels from both superficial and deep plexuses of optical coherence tomography angiography (OCTA) scans. Four significant retinal vasculature features are extracted, which reflect the changes in the retinal blood vessels due to DR progress. Finally, these extracted features are classified by using the random forest (RF) technique to differentiate the early DR from normal subjects. Our proposed system achieved an average accuracy of 98%, sensitivity of 98%, and specificity of 100%, which outperforms other state-of-the-art techniques.

The purpose of this work is to develop a computer-aided diagnosis (CAD) system for detecting and localizing prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) acquired at five distinct b-values. The first step in the proposed system depends on nonnegative matrix factorization (NMF) to fuse intensity features of prostate voxels, spatial features of neighboring voxels, and shape prior features to guide the evolution of a level set function for accurate prostate segmentation. The second step in the proposed system involves calculating the apparent diffusion coefficient (ADC) maps of the segmented prostate regions as a discriminating feature between malignant and healthy cases. These ADC maps are used in the last step of the CAD system to train a convolutional neural network (CNN)-based model to identify the ADC maps with malignant tumors. To evaluate the accuracy of the system, 50% of the ADC maps are randomly chosen to train the CNN-model while the second 50% of the ADC maps are used to evaluate the accuracy of the trained model. The proposed CAD system resulted in an average area under the receiver operating characteristic curve (AUC) of 0.93 at the five b-values.

Early diagnosis of pulmonary nodules is critical for lung cancer clinical management. In this paper, a novel framework for pulmonary nodule diagnosis, using descriptors extracted from single computed tomography (CT) scan, is introduced. This framework combines appearance and shape descriptors to give an indication of the nodule prior growth rate, which is the key point for diagnosis of lung nodules. Resolved Ambiguity Local Binary Pattern and 7thOrder Markov Gibbs Random Field are developed to describe the nodule appearance without neglecting spatial information. Spherical harmonics expansion and some primitive geometric features are utilized to describe how the nodule shape is complicated. Ultimately, all descriptors are combined using denoising autoencoder to classify the nodule, whether malignant or benign. Training, testing, and parameter tuning of all framework modules are done using a set of 727 nodules extracted from the Lung Image Database Consortium (LIDC) dataset. The proposed system diagnosis accuracy, sensitivity, and specificity were 94.95%, 94.62%, 95.20% respectively, all of which show that our system has promise to reach the accepted clinical accuracy threshold.

Non-invasive evaluation of renal transplant function is essential to minimize and manage renal rejection. A computer-assisted diagnostic (CAD) system was developed to evaluate kidney function post-transplantation. The developed CAD system utilizes the amount of blood-oxygenation extracted from 3D (2D + time) blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) to estimate renal function. BOLD-MRI scans were acquired at five different echo-times (2, 7, 12, 17, and 22) ms from 15 transplant patients. The developed CAD system first segments kidneys using the level-sets method followed by estimation of the amount of deoxyhemoglobin, also known as apparent relaxation rate (R2*). These R2* estimates were used as discriminatory features (global features (mean R2*) and local features (pixel-wise R2*)) to train and test state-of-the-art machine learning classifiers to differentiate between non-rejection (NR) and acute renal rejection. Using a leave-one-out cross-validation approach along with an artificial neural network (ANN) classifier, the CAD system demonstrated 93.3% accuracy, 100% sensitivity, and 90% specificity in distinguishing AR from non-rejection . These preliminary results demonstrate the efficacy of the CAD system to detect renal allograft status non-invasively.

Kidney segmentation from Dynamic Contrast Enhanced Magnetic Resonance Images (DCE-MRI) is an important step for the early detection of transplanted kidney rejection. In this paper, an accurate kidney segmentation method from DCE-MRI is proposed. In the proposed method, fuzzy c-means (FCM) algorithm is combined with a geometric deformable model (level set) method to accurately extract the kidney from its background. The FCM algorithm is applied to the input image and the obtained result is used as the initial contour for the level set method. The evolution of the level set boundary is controlled using the kidney shape prior model and the memberships of the pixels computed using the FCM algorithm. The proposed method has been tested on 40 subjects, and experimental results confirm the efficiency, reliability, and accuracy of the proposed method.

Pressure ulcer (PU) is a type of chronic wounds (CWs), which is remaining unhealed for a period longer than six weeks. PU results from applying pressure and friction on the skin of the patient for a long time. It has a complex structure as it has different kinds of tissues. Reliable assessment of PU is essential to the success of the treatment and care decision. In this paper, we propose a tissue classification system for PU based on 3D convolutional neural network (CNN). The main idea of the proposed system is to provide a 3D CNN network with five different models of the colored PU RGB images to accurately segment slough, granulation, and necrotic eschar tissues. Each model of the PU RGB image is provided to the CNN as an independent pathway. The first and second models are the original RGB PU images and its equivalent HSV images. The third model is the smoothed image by convolving the original image with a preselected Gaussian kernel. The last two models are the first-order models of the current and prior visual appearance. The models approximate empirical marginal probability distributions of voxel-wise signals with linear combinations of discrete Gaussians (LCDG). The proposed system was trained and tested on 193 color PU images. The proposed tissue segmentation system is evaluated by using three various metrics, which are the area under the ROC curve (AUC), the Dice similarity coefficient (DSC), and the percentage area distance (PAD). The system achieved an average AUC equals to 95%, DSC equals to 92%, and PAD equals to 10%, which are a promising result.

A novel framework for the classification of lung nodules using computed tomography (CT) scans is proposed in this paper. To get an accurate diagnosis of the detected lung nodules, the proposed framework integrates the following two groups of features: (i) appearance features that is modeled using higher-order Markov Gibbs random field (MGRF)-model that has the ability to describe the spatial inhomogeneities inside the lung nodule; and (ii) geometric features that describe the shape geometry of the lung nodules. The novelty of this paper is to accurately model the appearance of the detected lung nodules using a new developed 7th-order MGRF model that has the ability to model the existing spatial inhomogeneities for both small and large detected lung nodules, in addition to the integration with the extracted geometric features. Finally, a deep autoencoder (AE) classifier is fed by the above two feature groups to distinguish between the malignant and benign nodules. To evaluate the proposed framework, we used the publicly available data from the Lung Image Database Consortium (LIDC). We used a total of 727 nodules that were collected from 467 patients. The proposed system demonstrates the promise to be a valuable tool for the detection of lung cancer evidenced by achieving a nodule classification accuracy of 92.20%.

Recently, diffusion-weighted magnetic resonance imaging (DW-MRI) has been explored for non-invasive assessment of renal transplant functions. In this paper, a computer-aided diagnostic (CAD) system is developed to assess renal transplant functionality, which integrates both clinical and diffusion MRI -derived markers extracted from 4D DW-MRI (i.e. 3D + b-value). To extract the DW-MR image-markers, our framework performs multiple image processing steps, including kidney segmentation using a level-set approach and estimation of image-markers. To extract these image-markers, apparent diffusion coefficients (ADCs) are estimated from the segmented DW-MRIs and cumulative distribution functions (CDFs) of the ADCs are constructed at different b-values (i.e. gradient field strengths and duration). Finally, these markers (i.e. CDFs) are integrated with clinical biomarkers (e.g., creatinine clearance and serum plasma creatinine) to assess transplant status using stacked auto-encoders with non-negativity constraints based on deep learning classification approach. Our CAD system consists of two consecutive classification stages. The first stage classifier achieved a 96% accuracy, a 95% sensitivity, and a 100% specificity in distinguishing non-rejection (NR) from dysfunctional (DF) transplanted kidneys. Additionally, an overall accuracy of 94% has been obtained in the second stage in separating DF to acute rejection (AR) and different renal disease (DRD) transplants. Our preliminary results hold strong promise that the presented CAD system is of a high reliability to non-invasively diagnose renal transplant status.

This paper introduces a 3D segmentation approach using an adaptive patient-specific retinal atlas and an appearance model for 3D Optical Coherence Tomography (OCT) data. In order to reconstruct the 3D patient-specific retinal atlas, we started by segmenting the macula central area where the fovea is clearly identified in the data to be segmented. The segmentation of this selected foveal area inside the retina is accomplished by using joint Markov Gibbs Random Field (MGRF) integrating shape, intensity, and spatial information of 12 retinal layers. A 2D shape prior was built using a series of co-registered training OCT images that were collected from 200 different subjects. The shape prior was then adapted to the first order appearance and second order spatial interaction MGRF model of the data to be segmented. Once the middle of the macula “foveal area” had been segmented, its segmented layers' labels and their appearances were used to segment the adjacent slices. The previous step was propagated until the complete 3D OCT patient-data was segmented. The proposed approach was tested on 30 different subjects, with either normal or pathological OCT scans, and then compared with a delineated ground truth and the results were then verified by retina specialists. Performance was measured using the Dice Similarity Coefficient (DSC), agreement coefficient (AC), and average deviation (AD) metrics. The accuracy achieved by the segmentation approach clearly demonstrates the promise of the proposed segmentation approach and shows improvement over a state-of-the-art 3D OCT segmentation approach currently in use.

To improve the accuracy of segmenting medical images from different modalities we propose to integrate three types of comprehensive quantitative image descriptors with a deep 3D convolutional neural network. The descriptors include: (i) a Gibbs energy for a prelearned 7th-order Markov-Gibbs random field (MGRF) model of visual appearance, (ii) a relearned adaptive shape prior model, and a first-order conditional random field model of visual appearance of regions at each current stage of segmentation. The neural network fuses the computed descriptors, together with the raw image data, for obtaining the final voxel-wise probabilities of the goal regions. Quantitative assessment of our framework in terms of Dice similarity coefficients, 95-percentile bidirectional Hausdorff distances, and percentage volume differences confirms the high accuracy of our model on 95 CT lung images (98.37±0.68%,2.79±1.32 mm,3.94±2.11%) and 95 diffusion weighted kidney MRI (96.65±2.15%,4.32±3.09 mm,5.61±3.37%), respectively.

The following topics are dealt with: learning (artificial intelligence); feature extraction; image classification; feedforward neural nets; neural nets; convolution; object detection; image segmentation; face recognition; image representation.

Alzheimer's disease (AD) is a behavioral and cognitive neurodegenerative disorder whose sufferers exceed 5.5 million Americans. Among its stages, the early diagnosis of AD is considered the main research issue due to many factors including the variable effects of the disease through its patients. This paper targets the personalized diagnosis of AD through presenting a local/regional analysis system that represents the degree of regional abnormalities using detailed parcellation of the brain. For more detailed results, the statistical analysis was applied for restricting the diagnosis to the statistically determined significant brain regions. The system's evaluation shows promising results with an average accuracy, specificity, and sensitivity between the three tested groups of 98%, 99.09%, and 96.48%, respectively.

The ultimate goal of this paper is to develop a novel personalized comprehensive computer aided diagnostic (CAD) system for precise diagnosis of autism spectrum disorder (ASD) based on the 3D shape analysis of the cerebral cortex (Cx), To achieve the main goal of the proposed system, we used structural MRI modality (sMRI) to be able to extract the shape features of the brain cortex. After segmenting the brain cortex from sMRI, we used a spherical harmonics analysis to measure the surface complexity, in addition to studying surface curvatures. Finally, a multi-stage deep network based on several autoencoders and softmax classifiers is constructed to provide the final global diagnosis. The presented CAD system was tested on several datasets, achieving an average accuracy of 92.15%. In addition to its global diagnostic accuracy, the local diagnostic accuracies of the most significant areas also demonstrated the ability of the proposed system to construct very promising local maps of ASD-related brain abnormalities, which can be considered an important step towards personalized medicine for autistic individuals.

This paper introduces a diagnosis system for detecting early signs of diabetic retinopathy (DR) using optical coherence tomography angiography (OCTA) images. We developed a segmentation technique that was able to extract blood vessels from both retinal superficial and deep maps. It is based on a higher order joint Markov-Gibbs random field (MGRF) model, which combines both current and spatial appearance information of retinal blood vessels. To be able to train/test a support vector machine (SVM) classifier, three local features were extracted from the segmented images. These extracted features are the density and appearance of the retinal blood vessels in addition to the distance map of the foveal avascular zone (FAZ). Then, we used SVM with linear kernel to distinguish sub-clinical DR patients from normal cases. By using 105 subjects, the presented computer-aided diagnosis (CAD) system demonstrated an overall accuracy (ACC) of 97.3 % and a Dice similarity coefficient (DSC) of 97.9%.

Pressure ulcer (PU) is a clinical pathology of localized deterioration to the underlying tissues as well as to the skin, which is generated by friction and pressure. A trustworthy diagnosis of PU, which is supported by accurate assessment, is critical to have effective therapy and save the patient's life. In this paper, we propose an automatic classification framework to segment and classify various tissues to help in diagnosis and treatment of PU. The proposed framework consists of two main stages, which are region of interest (ROI) extraction and tissue segmentation stages. The main idea is to extract various models and features from PU RGB images and supply them to multi-path 3D convolution neural network (CNN) to segment slough, necrotic eschar, and granulation tissues to help in assessing the status of PU. ROI is extracted by supplying three different color models to the CNN, which are RGB, HSV, and YCbCr. Then, the PU tissues are classified by providing four various models to the 3D CNN. These models are the original RGB image, the smoothed image with a pre-selected Gaussian kernel, and the 1st-order models of prior and current visual appearance. The framework was trained and tested on 100 color RGB PU images. The classification accuracy was evaluated using the area under the curve (AUC), the percentage area distance (PAD), and Dice similarity coefficient (DSC). The obtained preliminary results have AUC of 96%, PAD of 10%, and DSC of 93%. These experimental results are promising and can lead to an accurate assessment of the PU status.

This paper addresses the issue of early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) using a convolutional neural network (CNN) based computer-aided diagnosis (CAD) system. The proposed CNN-based CAD system first segments the prostate using a geometric deformable model. The evolution of this model is guided by a stochastic speed function that exploits first- and second-order appearance models besides shape prior. The fusion of these guiding criteria is accomplished using a nonnegative matrix factorization (NMF) model. Then, the apparent diffusion coefficients (ADCs) within the segmented prostate are calculated at each b-value. They are used as imaging markers for the blood diffusion of the scanned prostate. For the purpose of classification/diagnosis, a three dimensional CNN has been trained to extract the most discriminatory features of these ADC maps for distinguishing malignant from benign prostate tumors. The performance of the proposed CNN-based CAD system is evaluated using DWI datasets acquired from 45 patients (20 benign and 25 malignant) at seven different b-values. The acquisition of these DWI datasets is performed using two different scanners with different magnetic field strengths (1.5 Tesla and 3 Tesla). The conducted experiments on in-vivo data confirm that the use of ADCs makes the proposed system nonsensitive to the magnetic field strength.

This manuscript presents a Computer Aided Diagnosis (CAD) system to assist in the early diagnosis of Alzheimer's disease (AD) with the ability to provide a personalized diagnosis by visualizing the detected abnormality per brain regions (AAL atlas). The CAD system utilizes PiB-PET scans and consists of the following four essential stages-(1) a preprocessing step performs data reorientation, co-registration, and spatial normalization; (2) partitioning the brain into 116 labeled regions utilizing a brain atlas to facilitate local diagnosis; (3) extraction of features within each region using scale-invariant Laplacian of Gaussian (LoG) that detects the maximum or minimum of a radially symmetric intensity distribution; and (4) construction of two diagnosis layers (local and global) using a Support Vector Machine (SVM) classifier and its probabilistic variant (pSVM). The CAD system was tested on 84 PiB-PET scans (19 normal control (NC) and 65 mild cognitive impairment (MCI)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The proposed system had a classification accuracy, sensitivity, and specificity of 100%.

This paper introduces a novel shape-based computer-aided diagnosis (CAD) system using magnetic resonance (MR) brain images for autism diagnosis at different life stages. To improve the classification robustness, the system fuses the shape features extracted from the cerebral cortex (Cx) and cerebral white matter (CWM). Fusion is conducted based on the findings suggesting that Cx changes in autism are related to CWM abnormalities. The CAD system starts with segmenting Cx and CWM using a 3D joint model that combines intensity, shape, and spatial information. Then, Spherical Harmonic (SPHARM) is applied to the re-constructed meshes of Cx to derive 4 metrics for each mesh point; normal curvature, mean curvature, gaussian curvature, and Cx surface reconstruction error. To analyze the CWM shape, distance maps of its gyri are computed and three more shape features are extracted for these gyri. Finally, all the extracted shape features are fed to a multi-level deep network for feature fusion and diagnosis. The CAD system has been evaluated using subjects from the ABIDE database (8–12.8 years), achieving an accuracy of 93%, and from NDAR/Pitt database (16–51 years), achieving an accuracy of 97%. Also in order to show the capability of the system for early diagnosis, it has been tested on NDAR/IBIS database for infants, resulting in an accuracy of 85%. These initial results on the 3 databases hold the promise of efficient autism diagnosis.

Spinal cord injured (SCI) individuals are often subject to skeletal muscles deterioration and adipose tissue gain in paralyzed muscles. These negative impacts can limit motor functions and lead to secondary complications such as diabetes, cardiovascular diseases and metabolic syndrome. In this study, we proposed an accurate and fast automatic framework for thigh muscle and fat volume segmentation using magnetic resonance 3-D images, which is aimed at quantifying the impact of SCI and different rehabilitative interventions for these individuals. In this framework, the subcutaneous, intermuscular fat volumes were segmented using a Linear Combination of Discrete Gaussians (LCDG) algorithm. In order to segment muscle group volumes, each MRI volume was initially registered to a training database using a 3-D Cubic B-splines based method. As a second step, a 3-D level-set method was developed utilizing the Joint Markov Gibbs Random Field (MGRF) model that integrates first order appearance model of the muscles, spatial information, and shape model to localize the muscle groups. The results of testing the new method on 15 MRI datasets from 10 SCI and 5 non-disabled subjects showed accuracy of 87.10% for fat segmentation and 96.71% for muscle group segmentation based on Dice similarity coefficient measurements.

This paper proposes a novel framework for the classification of lung nodules using computed tomography (CT) scans. The proposed framework is based on the integrating the following features to get accurate diagnosis of detected lung nodules: (i) Spherical Harmonics-based shape features that have the ability to describe the shape complexity of the lung nodules; (ii) Higher-Order Markov Gibbs Random Field (MGRF)-based appearance model that has the ability to describe the spatial inhomogeneities in the lung nodule; and (iii) volumetric features that describe the size of lung nodules. To accurately model the surface/shape of the detect lung nodules, we used spherical harmonics expansion due to its ability to approximate the surfaces of complicated shapes. We will use the reconstruction error curve as a new metric to describe the shape complexity of the detected lung nodules. Moreover, we developed a new higher 7th-order MGRF model that has the ability to model the existing the spatial inhomogeneities for both small and large detected lung nodules. Finally, a deep autoencoder (AE) classifier is fed by the above three features to distinguish between the malignant and benign nodules. To evaluate the proposed framework, we used the publicly available data from the Lung Image Database Consortium (LIDC). We used a total of 116 nodules that were collected from 60 patients. By achieving a classification accuracy of 96.00%, the proposed system demonstrates promise to be a valuable tool for the detection of lung cancer.

A novel framework for the detection of radiation-induced lung injury (RILI) from 4D computed tomography (CT) has been proposed. Our framework performs 4D-CT lung fields segmentation, deformable image registration (DIR), extraction of textural and functional features, and classification of lung voxels using deep 3D convolutional neural networks (CNN). The 4D-CT images segmentation extracts the lung fields inside the exhale phase using our multi-scale Gaussian adaptive shape prior technique followed by label propagation to other 4D-CT phases using a newly developed adaptive shape model. Then, the 4D-CT DIR locally aligns consecutive phases of the respiratory cycle using the 3D Laplace equation for finding voxel correspondences between the iso-surfaces for the fixed and moving lungs and generalized Gaussian Markov random field (GGMRF) as an anatomical consistency constraint. In addition to common lung functionality features, such as ventilation and elasticity, specific regional textural features are estimated by modeling the segmented images as samples of a novel 7th-order contrast-offset-invariant Markov-Gibbs random field (MGRF). Finally, a deep 3D CNN is applied to distinguish between the injured and normal lung tissues. 4D-CT datasets collected from 13 patients, who undergone the radiation therapy (RT), have been used in the evaluation of the proposed framework. The experimental results show the promise of our framework.

To accurately segment pathological and healthy lungs for reliable computer-aided disease diagnostics, a stack of chest CT scans is modeled as a sample of a spatially inhomogeneous joint 3D Markov-Gibbs random field (MGRF) of voxel-wise lung and chest CT image signals (intensities). The proposed learnable MGRF integrates two visual appearance sub-models with an adaptive lung shape submodel. The first-order appearance submodel accounts for both the original CT image and its Gaussian scale space (GSS) filtered version to specify local and global signal properties, respectively. Each empirical marginal probability distribution of signals is closely approximated with a linear combination of discrete Gaussians (LCDG), containing two positive dominant and multiple sign-alternate subordinate DGs. The approximation is separated into two LCDGs to describe individually the lungs and their background, i.e., all other chest tissues. The second-order appearance submodel quantifies conditional pairwise intensity dependencies in the nearest voxel 26-neighborhood in both the original and GSS-filtered images. The shape submodel is built for a set of training data and is adapted during segmentation using both the lung and chest appearances. The accuracy of the proposed segmentation framework is quantitatively assessed using two public databases (ISBI VESSEL12 challenge and MICCAI LOLA11 challenge) and our own database with, respectively, 20, 55, and 30 CT images of various lung pathologies acquired with different scanners and protocols. Quantitative assessment of our framework in terms of Dice similarity coefficients, 95-percentile bidirectional Hausdorff distances, and percentage volume differences confirms the high accuracy of our model on both our database (98.4±1.0%, 2.2±1.0mm, 0.42±0.10%) and the VESSEL12 database (99.0±0.5%, 2.1±1.6mm, 0.39±0.20%), respectively. Similarly, the accuracy of our approach is further verified via a blind evaluation by the organizers of the LOLA11 competition, where an average overlap of 98.0% with the expert’s segmentation is yielded on all 55 subjects with our framework being ranked first among all the state-of-the-art techniques compared.

This paper introduces a novel framework for segmenting retinal layers from optical coherence tomography (OCT) images. In order to account for the noise and inhomogeneity of OCT scans, especially for diseased ones, the proposed framework is based on unique joint model that combines shape, intensity, and spatial information, and is able to segment 12 distinct retinal layers. First, the shape prior is built using a subset of co-aligned training OCT images. The alignment process is initialized using an innovative method that employs multi-resolution edge tracking which defines control points on the tracked retinal boundaries. The shape model is then adapted during the segmentation process using visual appearance characteristics that are described using pixel-wise image intensities and their spatial interaction features. In order to more accurately model the empirical grey level distribution of OCT images, a linear combination of discrete Gaussians (LCDG) is used that has positive and negative components. Also, in order to accurately account for noise, the model is integrated with a second-order Markov Gibbs random field (MGRF) spatial interaction model. The proposed approach was tested on 200 normal and diseased OCT scans (e.g. Age macular degeneration (AMD), diabetic retinopathy), having their ground truth delineated by retina specialists, then measured using the Dice similarity coefficient (DSC), agreement coefficient (AC1), and average deviation (AD) metrics. The accuracy achieved by the segmentation approach clearly demonstrates the promise it holds for robust segmentation of retinal layers which would aid in the early diagnosis of different retinal abnormalities.

Early diagnosis, playing an important role in preventing progress and treating the Alzheimer's disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocampus shape, cortical thickness, and brain volume. This paper proposed to predict the AD with a deep 3D convolutional neural network (3D-CNN), which can learn generic features capturing AD biomarkers and adapt to different domain datasets. The 3D-CNN is built upon a 3D convolutional autoencoder, which is pre-trained to capture anatomical shape variations in structural brain MRI scans. Fully connected upper layers of the 3D-CNN are then fine-tuned for each task-specific AD classification. Experiments on the CADDementia MRI dataset with no skull-stripping preprocessing have shown our 3D-CNN outperforms several conventional classifiers by accuracy. Abilities of the 3D-CNN to generalize the features learnt and adapt to other domains have been validated on the ADNI dataset.

A framework for 3D kidney segmentation from abdominal computed tomography (CT) images is proposed. Accurate kidney segmentation from CT images is a challenging task due to the large inhomogeneity of the kidney (e.g., cortex and medulla), inter-patient anatomical differences, etc. To account for these challenges, a novel framework utilizing random forest (RF) classification that has the ability to cluster complex data is proposed. To build a robust classification model, discriminative features are needed for better separation of data classes. In this work, regional features from the CT appearance, a kidney shape prior model, and higher-order spatial interactions are extracted and are used for tissue classification. The shape model is constructed using a set of training images and is updated during segmentation using an appearance-based method taking into account both voxels' locations and appearances. The spatial interactions between CT data voxels are modeled using a higher-order spatial model that adds to the pairwise cliques the families of the triple- and quad cliques. The proposed framework has been tested on CT data that has been collected from 20 subjects and consist of multiple 3D CT scans acquired at the pre-and post-contrast agent administration. Evaluation results, using both volumetric and distance-based metrics, between manually drawn and automatically segmented contours confirm the high accuracy of the proposed technique.

In this paper, we propose a novel non-invasive framework for the early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DW-MRI). The proposed approach consists of three main steps. In the first step, the prostate is localized and segmented based on a new level-set model. In the second step, the apparent diffusion coefficient (ADC) of the segmented prostate volume is mathematically calculated for different b-values. To preserve continuity, the calculated ADC values are normalized and refined using a Generalized Gauss-Markov Random Field (GGMRF) image model. The cumulative distribution function (CDF) of refined ADC for the prostate tissues at different b-values are then constructed. These CDFs are considered as global features describing water diffusion which can be used to distinguish between benign and malignant tumors. Finally, a deep learning auto-encoder network, trained by a stacked non-negativity constraint algorithm (SNCAE), is used to classify the prostate tumor as benign or malignant based on the CDFs extracted from the previous step. Preliminary experiments on 53 clinical DW-MRI data sets resulted in 100% correct classification, indicating the high accuracy of the proposed framework and holding promise of the proposed CAD system as a reliable non-invasive diagnostic tool.

Although renal biopsy remains the gold standard for diagnosing the type of renal rejection, it is not preferred due to its invasiveness, recovery time (1-2 weeks), and potential for complications, e.g., bleeding and/or infection. Therefore, there is an urgent need to explore a non-invasive technique that can early classify renal rejection types. In this paper, we develop a computer-aided diagnostic (CAD) system that can classify acute renal transplant rejection (ARTR) types early via the analysis of apparent diffusion coefficients (ADCs) extracted from diffusion-weighted (DW) MRI data acquired at low-(accounting for perfusion) and high-(accounting for diffusion) b-values. The developed framework mainly consists of three steps: (i) data co-alignment using a 3D B-spline-based approach (to handle local deviations due to breathing and heart beat motions) and segmentation of kidney tissue with an evolving geometric (level-set based) deformable model guided by a voxel-wise stochastic speed function, which follows a joint kidney-background Markov-Gibbs random field model accounting for an adaptive kidney shape prior and visual kidney-background appearances of DW-MRI data (image intensities and spatial interactions); (ii) construction of a cumulative empirical distribution of ADC at low and high b-values of the segmented kidney accounting for blood perfusion and water diffusion, respectively, to be our discriminatory ARTR types feature; and (iii) classification of ARTR types (acute tubular necrosis (ATN) anti-body- and T-cell-mediated rejection) based on deep learning of a non-negative constrained stacked autoencoder. Results show that 98% of the subjects were correctly classified in our “leave-one-subject-out” experiments on 39 subjects (namely, 8 out of 8 of the ATN group and 30 out of 31 of the T-cell group). Thus, the proposed approach holds promise as a reliable non-invasive diagnostic tool.

This paper proposes a novel framework for the identification of the radiation-induced lung injury (RILI) after radiation therapy (RT) using 4D computed tomography (CT) scans. The proposed methodology consists of four components: (i) elastic image registration; (ii) segmentation of the lung fields; (iii) extraction of functional and texture features; and (iv) classification of the lung tissues. The registration step locally aligns the consecutive phases of the respiratory cycle using an elastic image registration approach based on descent minimization of the sum of squared difference similarity metric. Secondly, lung fields are segmented using a hybrid framework that integrates an adaptive shape prior model, a first-order intensity model, and a second order homogeneity descriptor of the lung tissues. Next, regional features that describe both the texture features using the novel 7th-order Markov-Gibbs random field (MGRF) model in addition to the lung functionality features (e.g., ventilation and elasticity) are estimated from a segmented lungs. Finally, a random forest classifier (RF) is applied to distinguish between injured and normal lung tissues. To evaluate the proposed framework, we used data sets that have been collected from 13 patients who had underwent RT treatment. Experimental results demonstrate the promise of the proposed framework for the identification of the injured lung region, and thus hold the promise as a valuable tool for early detection of RILI.

This paper introduces a novel computer-aided diagnostic (CAD) system for the assessment of renal transplant status that integrates image-based biomarkers derived from 4D (3D + b -value) diffusion-weighted (DW) MRI, and clinical biomarkers. To analyze DW-MRI, our framework starts with kidney tissue segmentation using a level set approach after DW-MRI data alignment to handle the motion effects. Secondly, the cumulative empirical distributions (i.e., CDFs) of apparent diffusion coefficients (ADCs) of the segmented DW-MRIs are estimated at low and high gradient strengths and duration ( b -values) accounting for both blood perfusion and diffusion, respectively. Finally, these CDFs are fused with laboratory-based biomarkers (creatinine clearance and serum plasma creatinine) for the classification of transplant status using a deep learning-based classification approach utilizing a stacked non-negativity constrained auto-encoder. Using “leave-one-subject-out” experiments on a cohort of 58 subjects, the proposed CAD system distinguished non-rejection transplants from kidneys with abnormalities with a 95 % accuracy (sensitivity = 95 %, specificity = 94 %) and achieved a 95 % correct classification between early rejection and other kidney diseases. Our preliminary results demonstrate the promise of the proposed CAD system as a reliable non-invasive diagnostic tool for renal transplants assessment.

In this paper, we propose a novel framework for the automated extraction of the brain from T1-weighted MR images. The proposed approach is primarily based on the integration of a stochastic model [a two-level Markov-Gibbs random field (MGRF)] that serves to learn the visual appearance of the brain texture, and a geometric model (the brain isosurfaces) that preserves the brain geometry during the extraction process. The proposed framework consists of three main steps: 1) Following bias correction of the brain, a new three-dimensional (3-D) MGRF having a 26-pairwise interaction model is applied to enhance the homogeneity of MR images and preserve the 3-D edges between different brain tissues. 2) The nonbrain tissue found in the MR images is initially removed using the brain extraction tool (BET), and then the brain is parceled to nested isosurfaces using a fast marching level set method. 3) Finally, a classification step is applied in order to accurately remove the remaining parts of the skull without distorting the brain geometry. The classification of each voxel found on the isosurfaces is made based on the first- and second-order visual appearance features. The first-order visual appearance is estimated using a linear combination of discrete Gaussians (LCDG) to model the intensity distribution of the brain signals. The second-order visual appearance is constructed using an MGRF model with analytically estimated parameters. The fusion of the LCDG and MGRF, along with their analytical estimation, allows the approach to be fast and accurate for use in clinical applications. The proposed approach was tested on in vivo data using 300 infant 3-D MR brain scans, which were qualitatively validated by an MR expert. In addition, it was quantitatively validated using 30 datasets based on three metrics: the Dice coefficient, the 95% modified Hausdorff distance, and absolute brain volume difference. Results showed the capability of the proposed approach, outperforming four widely used BETs: BET, BET2, brain surface extractor, and infant brain extraction and analysis toolbox. Experiments conducted also proved that the proposed framework can be generalized to adult brain extraction as well.

Accurate segmentation of pathological lungs from large-size chest computed tomographic images is crucial for computer-assisted lung cancer diagnostics. In this paper, a new framework for automatic pathological lung segmentation is proposed. The proposed INMF-based segmentation approach has the ability to handle the in-homogeneities caused by the arteries, veins, bronchi, and possible pathologies that may exist in the lung tissues, and to detect the number of clusters in the image in an automated manner. The proposed INMF-based segmentation framework is quantitatively validated on simulated realistic lung phantoms that mimic different lung pathologies (7 datasets), in vivo data sets for 17 subjects, and for lung disease with severe pathologies. Three metrics are used: the Dice coefficient, modified Hausdorff distance, and absolute lung volume difference. Results show that the proposed approach outperforms existing lung segmentation techniques and can handle in-homogenities caused by different pathologies.

This paper introduces a new framework for the segmentation of different brain structures from 3D infant MR brain images. The proposed segmentation framework is based on a shape prior built using a subset of co-aligned training images that is adapted during the segmentation process based on higher-order visual appearance characteristics of infant MRIs. These characteristics are described using voxel-wise image intensities and their spatial interaction features. In order to more accurately model the empirical grey level distribution of infant brain signals, a Linear Combination of Discrete Gaussians (LCDG) is used that has positive and negative components. Also to accurately account for the large inhomogeneity in infant MRIs, a higher-order Markov Gibbs Random Field (MGRF) spatial interaction model that integrates third- and fourth-order families with a traditional second-order model is proposed. The proposed approach was tested on 40 in-vivo infant 3D MR brain scans, having their ground truth created by an expert radiologist, using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute brain volume difference. Experimental results promise an accurate segmentation of infant MR brain images compared to current open source segmentation tools.

This paper introduces a novel adaptive atlas-based framework for the automated segmentation of different brain structures from infant magnetic resonance (MR) brain images. The proposed framework provides a more accurate segmentation of different infant brain structures in the isointense age stage (6–12 months) by integrating diffusion tensor imaging (DTI) image features (e.g., fractional anisotropy (FA)) in the segmentation procedure. The input to the proposed system is the medical scans of the infant brain, i.e., 4D diffusion weighted images (DWI). The input brain first undergoes a quality control procedure to remove scan artifacts, and correct motion and eddy current distortions, followed by brain extraction, in which any non-brain tissues are removed. Then, specific DTI features are extracted, and fused to guide the segmentation process to produce the final segmented brain tissues. The high accuracy of the proposed segmentation approach was confirmed by testing it on 10 in-vivo diffusion weighted infant MR brain data sets using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute volume difference.

Developing any non-invasive computer-aided diagnostic (CAD) system for the diagnosis of kidney diseases essentially requires the extraction of the kidney from medical images. We propose a shape based level-set framework for 3D kidney segmentation from diffusion-weighted magnetic resonance imaging (DW-MRI). A stochastic speed relationship is used to control the deformable model evolutions. This speed relationship is based on an adaptive shape prior guided by the first- and second-order visual appearance features of the DW-MRI data. These pre-mentioned image features are integrated into a joint Markov-Gibbs random field (MGRF) model of the kidney and its background. DW-MRI data sets from eight subjects acquired at different b-values ranging from 0 to 1000 s/mm2are tested using a leave-one-subject-out method to evaluate the proposed segmentation approach, and to compare its performance with other segmentation methods using three evaluation metrics: the Dice similarity coefficient (DSC), the 95-percentile modified Hausdorff distance, and the absolute kidney volume difference. Robustness and accuracy of the proposed approach are confirmed through the experimental results' evaluation between manually drawn and automatically segmented contours.

A novel framework for precise segmentation of pathological lung tissues from computed tomography (CT) is presented. The proposed segmentation method is based on a novel 3D joint Markov-Gibbs random field (MGRF) model that integrates three features: (i) the first-order visual appearance model of the CT image, (ii) the second-order spatial interaction model of the CT image, and (iii) a shape prior model of the lung. The first-order appearance model describes the empirical distribution of image signals using a linear combination of Discrete Gaussians (LCDG) with positive and negative components. The second order spatial interaction model describes the relation between the CT image signals using a pairwise MGRF spatial model of independent image signals and interdependent region labels. The shape prior is constructed from a set of training CT data, collected from different subjects. Experiments on 20 datasets with different types of pathologies confirm high accuracy of the proposed approach compared with other lung segmentation methods.

This paper presents a novel approach for extracting the brain from 3D T1-weighted MR images. The proposed approach combines a stochastic two-level Markov-Gibbs random field (MGRF) image model with a geometric model that parcels the brain into a set of nested iso-surfaces using a fast marching level setmethod. The classification of each brain voxel found on the iso-surfaces is performed based on the first-order (a linear combination of discrete gaussian (LCDG) model) and second-order (an MGRF model with analytically estimated parameters) visual appearance features of the brain structures. Our approach is tested on 280 infant 3D MR brain scans and evaluated on 9 data sets using the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Experimental results showed that the fusion of the stochastic and geometric models of brain MRI data has led to more accurate brain extraction, when compared with other widely-used brain extraction tools, such as BET, BET2, and brain surface extractor (BSE).

In this paper, a new framework for 3D lung segmentation is proposed. The primary step of this framework is to model both the spatial interaction and first-order visual appearance of the lung tissue based on a new Nonnegative Matrix Factorization (NMF) approach that has the ability to handle the inhomogeneity in the lung regions caused by arteries, veins, bronchi, and possible pathological tissues. The performance of our framework is assessed on fourteen 3D CT images. Based on the Dice Similarity Coefficient (DSC), experimental results showed that the proposed approach outperforms other lung segmentation techniques.

This paper introduces a new adaptive atlas-based framework for the automated segmentation of different brain structures from infant diffusion tensor images (DTI). To model the brain images and their desired region maps, we used a joint Markov-Gibbs random field (MGRF) model that accounts for three image descriptors: (i) a 1st-order visual appearance to describe the empirical distribution of DTI extracted features, (ii) an adaptive shape model, and (iii) a 3D spatially invariant 2nd-order MGRF homogeneity descriptor. The 1st-order visual appearance descriptor is accurately modeled using a linear combination of discrete Gaussians (LCDG) model having positive and negative components. The proposed adaptive shape model is constructed from a prior atlas database built using a subset of co-aligned training data sets that is adapted during the segmentation process guided by the visual appearance characteristics of several DTI features. To accurately account for the large inhomogeneity of infant brains, the homogeneity descriptor is modeled by a 2nd-order translation and rotation invariant MGRF of region labels with analytically estimated potentials. The high accuracy of our segmentation approach was confirmed by testing it on 10 in-vivo infant DTI brain data sets using three metrics: the Dice similarity coefficient, the 95-percentile modified Hausdorff distance, and the absolute brain volume difference.

A novel framework for assessing wall thickening from 4D cine cardiac magnetic resonance imaging (CMRI) is proposed. The proposed approach is primarily based on using geometrical features to track the left ventricle (LV) wall during the cardiac cycle. The 4D tracking approach consists of the following two main steps: (i) Initially, the surface points on the LV wall are tracked by solving a 3D Laplace equation between two successive LV surfaces; and (ii) Secondly, the locations of the tracked LV surface points are iteratively adjusted through an energy minimization cost function using a generalized Gauss-Markov random field (GGMRF) image model in order to remove inconsistencies and preserve the anatomy of the heart wall during the tracking process. Then the myocardial wall thickening is estimated by co-allocation of the corresponding points, or matches between the endocardium and epicardium surfaces of the LV wall using the solution of the 3D Laplace equation. Experimental results on in vivo data confirm the accuracy and robustness of our method. Moreover, the comparison results demonstrate that our approach outperforms 2D wall thickening estimation approaches.

The survey outlines and compares popular computational techniques for quantitative description of shapes of major structural parts of the human brain, including medial axis and skeletal analysis, geodesic distances, Procrustes analysis, deformable models, spherical harmonics, and deformation morphometry, as well as other less widely used techniques. Their advantages, drawbacks, and emerging trends, as well as results of applications, in particular, for computer-aided diagnostics, are discussed.

A novel framework for the classification of acute rejection versus nonrejection status of renal transplants from 2-D dynamic contrast-enhanced magnetic resonance imaging is proposed. The framework consists of four steps. First, kidney objects are segmented from adjacent structures with a level set deformable boundary guided by a stochastic speed function that accounts for a fourth-order Markov-Gibbs random field model of the kidney/background shape and appearance. Second, a Laplace-based nonrigid registration approach is used to account for local deformations caused by physiological effects. Namely, the target kidney object is deformed over closed, equispaced contours (iso-contours) to closely match the reference object. Next, the cortex is segmented as it is the functional kidney unit that is most affected by rejection. To characterize rejection, perfusion is estimated from contrast agent kinetics using empirical indexes, namely, the transient phase indexes (peak signal intensity, time-to-peak, and initial up-slope), and a steady-phase index defined as the average signal change during the slowly varying tissue phase of agent transit. We used a kn-nearest neighbor classifier to distinguish between acute rejection and nonrejection. Performance of our method was evaluated using the receiver operating characteristics (ROC). Experimental results in 50 subjects, using a combinatoric kn-classifier, correctly classified 92% of training subjects, 100% of the test subjects, and yielded an area under the ROC curve that approached the ideal value. Our proposed framework thus holds promise as a reliable noninvasive diagnostic tool.

A new framework for the precise segmentation of lung tissues from Computed Tomography (CT) is proposed. The CT images, Gaussian Scale Space (GSS) data generation using Gaussian Kernels (GKs), and desired maps of regions (lung and the other chest tissues) are described by a joint Markov-Gibbs Random Field Model (MGRF) of independent image signals and interdependent region labels. We focus on the most accurate model identification of the joint MGRF models. To better specify region borders, each empirical distribution of signals is rigorously approximated by a Linear Combination of Discrete Gaussians (LCDG) with positive and negative components. The classical Expectation-Maximization (EM) algorithm has been adapted for the LCDG model. The initial segmentations from the original and the generated GSS CT images are based on the LCDG-models; then they are iteratively refined using an MGRF model with analytically estimated potentials. Finally, these initial segmentations are fused together using a Bayesian fusion approach to get the final segmentation of the lung region. Experiments on eleven real data sets based on Dice Similarity Coefficient (DSC) metric confirms the high accuracy of the proposed approach.

A novel 2D approach for early assessment of malignant lung nodules based on analyzing the spatial distribution of Hounsfield values for the detected lung nodules is proposed. Spatial distribution of Hounsfield values comprising the malignant nodule appearance is accurately modeled with a new 2D rotationally invariant second-order Markov-Gibbs Random Field (MGRF). Preliminary experiments on 109 lung nodules (51 malignant and 58 benign) show that the proposed method is a promising supplement to current technologies (biopsy-based diagnostic systems) for the early diagnosis of lung cancer.

To estimate the number of unimodal components in a mixture model of a marginal probability distribution of signals while learning the model with a conventional Expectation-Maximization (EM) algorithm, a modification of the well-known Akaike information criterion (AIC) called the modified AIC (mAIC), is proposed. Embedding the mAIC into the EM algorithm allows us to exclude sequentially, one-by-one, the least informative components from their initially excessive, or over-fitting set. Experiments on modeling empirical marginal signal distributions with mixtures of continuous or discrete Gaussians in order to describe the visual appearance of synthetic phantoms and real medical 3D images (lung CT and brain MRI) demonstrate a marked and monotone increase of the mAIC towards its maximum at the proper number that is known for the synthetic phantom or practically justified for the real image. These results confirm the accuracy and robustness of the proposed automated mAIC-EM based learning.

A novel non-invasive approach for the early diagnosis of prostate cancer from diffusion-weighted MRI is proposed. The proposed diagnostic approach consists of three main steps. The first step is to isolate the prostate from the surrounding anatomical structures based on a Maximum a Posteriori (MAP) estimate of a new log-likelihood function that accounts for the shape priori, the spatial interaction, and the current appearance of prostate tissues and its background (surrounding anatomical structures). In the second step, a nonrigid registration algorithm is employed to account for any local deformation between the segmented prostates at different b-values that could occur during the scanning process due to patient breathing and local motion. In the final step, a kn-Nearest Neighbor-based classifier is used to classify the prostate into benign or malignant based on four appearance features extracted from registered images. Moreover, in this paper we introduce a new approach to generate color maps that illustrate the propagation of diffusion in prostate tissues based on the analysis of the 3D spatial interaction of the change of the gray level values of prostate voxel using a Generalized Gauss-Markov Random Field (GGMRF) image model. Finally, the tumor boundaries are determined using a level set deformable model controlled by the diffusion information and the spatial interactions between the prostate voxels. Experimental results on 28 clinical diffusion-weighted MRI data sets yield promising results.

Accurate registration of cardiac first-pass magnetic resonance imaging (FP-MRI) is fundamental for precise analysis of myocardial perfusion. In this paper, we introduce and validate a new framework for accurate registration of the segmented left ventricle (LV) wall on cardiac FP-MRI. Due to the continuous physiological motion of the heart that causes the LV wall to change shape significantly and to move within and through the image plane, we developed a new methodology for 2D FP-MRI nonrigid registration that includes: (i) global target-to-reference frame-to-frame alignment based on the maximization of the normalized mutual information (NMI); (ii) local alignment based on using a B-splines transformation model that maximizes a similarity function that accounts for 1st- and 2nd-order NMI between the globally aligned frames followed by (iii) a refinement step that is based on deforming each pixel of the target wall over evolving closed equi-spaced contours (iso-contours) to closely match the reference wall. Respective iso-contours in both reference and target frames are matched based on solving the Laplace equation. We have tested our framework on both synthetic phantoms and 20 in-vivo data sets that have been collected from patients with ischemic damage from heart attacks, who are undergoing a novel myoregeneration therapy.

To reduce noise within a tag line, unsharpen the tag edges in spatial domain, and amplify the tag-to-background contrast, a 3D energy minimization framework for the enhancement of tagged Cardiac Magnetic Resonance (CMR) image sequences, based on learning first- and second-order visual appearance models, is proposed. The first-order appearance modeling uses adaptive Linear Combinations of Discrete Gaussians (LCDG) to accurately approximate the empirical marginal probability distribution of CMR signals for a given sequence, and separates tag and background submodels. It is also used to classify the tag lines and the background. The second-order model considers image sequences as samples of a translation- and rotation-invariant 3D Markov-Gibbs Random Field (MGRF) with multiple pairwise voxel interactions. A 3D energy function for this model is built by using the analytical estimation of the spatio-temporal geometry and Gibbs potentials of interaction. To improve the strain estimation, by enhancing the tag and background homogeneity and contrast, the given sequence is adjusted using comparisons to the energy minimizer. Special 3D geometric phantoms, motivated by statistical analysis of the tagged CMR data, have been designed to validate the accuracy of our approach. Experiments with the phantoms and eight real data sets have confirmed the high accuracy of the functional parameters that are estimated for the enhanced tagged sequences when using popular spectral techniques, such as spectral Harmonic Phase (HARP).

Dyslexia severely impairs learning abilities; therefore, improved diagnostic methods are needed. Neuropathological studies have revealed an abnormal anatomy of the corpus callosum (CC) in dyslexic brains. We propose a new approach for the quantitative analysis of 3-D magnetic resonance images (MRI) of the brain that ensures a more accurate quantification of anatomical differences between the CC of dyslexic and control subjects. The proposed approach consists of three main processing steps: 1) segmenting the CC from a given 3-D MRI using the learned CC shape and visual appearance; 2) extracting the centerline of the CC; and 3) cylindrical mapping of the CC surface for its comparative analysis. Validation on 3-D simulated phantoms demonstrates the ability of the proposed approach to accurately detect the shape variability between two 3-D surfaces. Experimental results revealed significant differences (at the 95% confidence level) between 14 normal and 16 dyslexic subjects in all four anatomical divisions, i.e., splenium, rostrum, genu, and body of their CCs. Moreover, the initial classification results based on the centerline length and CC thickness suggest that the proposed shape analysis is a promising supplement to the current techniques for diagnosing dyslexia.

A novel automated framework for the segmentation of the left ventricle (LV) wall from contrast enhanced cardiac magnetic resonance images (CE-CMRI) is proposed. The framework consists of two main steps. First, the inner cavity of the LV is segmented from the surrounding tissues based on finding the Maximum A Posteriori (MAP) estimation of a new energy function using a graph-cuts-based optimization algorithm. The proposed energy function consists of three descriptors: 1st-order visual appearance descriptors of the CE-CMRI, a 2D spatially rotation-variant 2nd-order homogeneity descriptor, and a LV inner cavity shape descriptor. Second, the outer contour of the LV is segmented by generating an orthogonal wave, starting from the LV inner contour, by solving an Eikonal partial differential equation with a new speed function that combines the prior shape and current visual appearance models of the LV wall. The proposed framework was tested on in-vivo CE-CMR images and validated with manual expert delineations of left ventricle borders. Experiments and comparison results on real CE-CMR images confirm the robustness and accuracy of the proposed framework over the existing ones.

Prostate segmentation is an essential step in developing any non-invasive Computer-Assisted Diagnostic (CAD) system for the early diagnosis of prostate cancer using Magnetic Resonance Images (MRI). In this paper, a novel framework for 3D segmentation of the prostate region from Diffusion-Weighted Magnetic Resonance Imaging (DW-MRI) is proposed. The framework is based on a Maximum A Posteriori (MAP) estimate of a new log-likelihood function that accounts for Markov-Gibbs shape and appearance models of the object-of-interest and its background. The framework was evaluated on in vivo prostate DW-MRI with available manual expert segmentation. The performance evaluation of the proposed segmentation approach, based on voxel-based and distance-based metrics between manually drawn and automatically segmented contours, confirmed the robustness and accuracy of the proposed segmentation approach.

A new automatic approach for the estimation of global indexes from short-axis cine cardiac magnetic resonance (CMR) images is proposed. The inner contour of the left ventricle (LV) is segmented with a level set-based deformable model. Its evolution is controlled by a specially designed stochastic speed function that accounts for a learned spatially variant statistical shape prior, a 1st-order visual appearance descriptor of the contour interior and exterior (associated with the object and background, respectively), and a spatially invariant 2nd-order homogeneity descriptor. After the inner contour delineation, the total cavity volume (time varying LV volume) data is used to estimate the LV global functional indexes, i.e., ejection fraction, systolic and diastolic slopes. Experiments with in-vivo CMR data, obtained from subjects with chronic ischemic heart disease and damage that is documented by viability MRI, confirm a high robustness and accuracy of the proposed approach.

Kidney segmentation is an essential step in developing any non-invasive Computer-Assisted Diagnostic (CAD) system for the early detection of acute renal rejection. This paper describes a 3-D approach for kidney segmentation from abdominal Computed Tomography (CT) images using a level set-based deformable model. Its evolution is controlled by a specially designed stochastic speed function that accounts for a shape prior and features of image intensity and spatial interactions. The shape prior is learned from the co-aligned 3-D kidney data. The current visual appearances are described with marginal gray level distributions obtained by separating their mixture over the kidney data. The spatial interactions between the kidney voxels are modeled by a 3-D 2nd-order translation and rotation variant Markov-Gibbs Random Field (MGRF) of “object-background” labels with analytically estimated potentials. The proposed approach has been evaluated on the CT data sets of 29 patients, yielding an average volumetric overlap error of 3.71%. The presented results indicate that combing CT images' characteristics into level set evolution leads to more accurate segmentation results.

To discriminate more accurately between dyslexic and normal brains, we detect the brain cortex variability through a spherical harmonic analysis that represents a 3D surface supported by the unit sphere, having a linear combination of special basis functions, called spherical harmonics (SHs). The proposed 3D shape analysis is carried out in five steps: (i) 3D brain cortex segmentation, with a deformable 3D boundary, controlled by two probabilistic visual appearance models (the learned prior and the estimated current appearance one); (ii) 3D Delaunay triangulation to construct a 3D mesh model of the brain cortex surface; (iii) mapping this model to the unit sphere; (iv) computing the SHs for the surface, and (v) determining the number of the SHs to delineate the brain cortex. We describe the brain shape complexity with a new shape index, the estimated number of the SHs, and use it for the K-nearest classification into the normal and dyslexic brains. Initial experiments suggest that our shape index is a promising supplement to the current dyslexia diagnostic techniques.

Study of cerebral white matter in the brain is an important medical problem which helps in better understanding of brain disorders like autism. The goal of this research is to segment the cerebral white matter from the input Magnetic Resonance Imaging (MRI) data. The present segmentation problem becomes extremely difficult due to i) the complex shape of the cerebral white matter and ii) the very low contrast between the white matter and the surrounding structures in the MRI data. We employ a novel probabilistic graph cut algorithm, where the edge capacity functions of the classical graph cut algorithm are modified according to the probabilities of pixels to belong to different segmentation classes. In order to separate the surrounding structures from the white matter, two appropriate geometric shape priors are introduced. Experimentation in 2D with 20 different datasets has yielded an average segmentation accuracy of 94.78%.

Our long-term research goal is to develop a fully automated, image-based diagnostic system for early diagnosis of pulmonary nodules that may lead to lung cancer. This paper focuses on validating our approach for monitoring the development of lung nodules detected in successive chest low dose computed tomography (LDCT) scans of a patient. Our methodology for monitoring the detected lung nodules includes 3-D LDCT data registration, which is non-rigid and involves two steps: (i) global target-to-prototype alignment of one scan to another using the learned prior appearance model followed by (ii) local alignment in order to correct for intricate relative deformations. This approach has been validated on elastic lung phantoms constructed using state-of-the-art microfluidics technology. The elastic lung phantoms are fabricated from a flexible transparent polymer, i.e., polydimethylsiloxane (PDMS). These Phantoms mimic the contractions and expansions of the lung and nodules seen during normal breathing. Experiments confirm the high accuracy of the proposed approach for measuring the growth rate of the detected lung nodules.

The importance of accurate early diagnostics of autism that severely affects personal behavior and communication skills cannot be overstated. Neuropathological studies have revealed an abnormal anatomy of the Corpus Callosum (CC) in autistic brains. We propose a new approach to quantitative analysis of three-dimensional (3D) magnetic resonance images (MRI) of the brain that ensures a more accurate quantification of anatomical differences between the CC of autistic and normal subjects. It consists of three main processing steps: (i) segmenting the CC from a given 3D MRI using the learned CC shape and visual appearance; (ii) extracting a centerline of the CC; and (iii) cylindrical mapping of the CC surface for its comparative analysis. Our experiments revealed significant differences (at the 95% confidence level) between 17 normal and 17 autistic subjects in four anatomical divisions, i.e. splenium, rostrum, genu and body of their CC.

A new speed function to guide evolution of a level-set based active contour is proposed for segmenting an object from its background in a given image. The guidance accounts for a learned spatially variant statistical shape prior, 1st-order visual appearance descriptors of the contour interior and exterior (associated with the object and background, respectively), and a spatially invariant 2nd-order homogeneity descriptor. The shape prior is learned from a subset of co-aligned training images. The visual appearances are described with marginal gray level distributions obtained by separating their mixture over the image. The evolving contour interior is modeled by a 2nd-order translation and rotation invariant Markov-Gibbs random field of object / background labels with analytically estimated potentials. Experiments to segment the inner cavity of heart cine images confirm robustness and accuracy of the proposed approach.

Dyslexia severely impairs learning abilities, so that improved diagnostic methods are called for. Neuropathological studies have revealed abnormal anatomy of the Corpus Callosum (CC) in dyslexic brains. We explore a possibility of distinguishing between dyslexic and normal (control) brains by quantitative CC shape analysis in 3D magnetic resonance images (MRI). Our approach consists of the three steps: (i) segmenting the CC from a given 3D MRI using the learned CC shape and visual appearance; (ii) extracting the centerline of the CC; and (iii) classifying the subject as dyslexic or normal based on the estimated length of the CC centerline using a _-nearest neighbor classifier. Experiments revealed significant differences (at the 95% confidence level) between the CC centerlines for 14 normal and 16 dyslexic subjects. Our initial classification suggests the proposed centerline-based shape analysis of the CC is a promising supplement to the current dyslexia diagnostics.

A new speed function to guide evolution of a level-set based active contour is proposed for segmenting an object from its background in a given image. The guidance accounts for a learned spatially variant statistical shape prior, 1st-order visual appearance descriptors of the contour interior and exterior (associated with the object and background, respectively), and a spatially invariant 2nd-order homogeneity descriptor. The shape prior is learned from a subset of co-aligned training images. The visual appearances are described with marginal gray level distributions obtained by separating their mixture over the image. The evolving contour interior is modeled by a 2nd-order translation and rotation invariant Markov-Gibbs random field of object/background labels with analytically estimated potentials. Experiments with kidney CT images confirm robustness and accuracy of the proposed approach.

A novel parametric deformable model of a goal object controlled by shape and appearance priors learned from co-aligned training images is introduced. The shape prior is built in a linear space of vectors of distances to the training boundaries from their common centroid. The appearance prior is modeled with a spatially homogeneous 2nd-order Markov-Gibbs random field (MGRF) of gray levels within each training boundary. Geometric structure of the MGRF and Gibbs potentials are analytically estimated from the training data. To accurately separate goal objects from arbitrary background, the deformable model is evolved by solving an Eikonal partial differential equation with a speed function combining the shape and appearance priors and the current appearance model. The latter represents empirical gray level marginals inside and outside an evolving boundary with adaptive linear combinations of discrete Gaussians (LCDG). The analytical shape and appearance priors and a simple Expectation-Maximization procedure for getting the object and background LCDGs, make our segmentation considerably faster than most of the known counterparts. Experiments with various images confirm robustness, accuracy, and speed of our approach.

This paper presents an image processing-based approach for the assessment of living cell apoptosis. The approach uses deformable models in tracing the changes in cell shapes in accordance to possible apoptotic cell death. Stochastic controlled energy function is used to drive the evolution of the deformable model. As an application for the proposed approach, it is applied for detecting the morphological changes in exercise-induced immune cells during their apoptosis. The approach is used with the goal of automating the assessment of cell apoptosis. The proposed approach shows promising results in detecting these morphological changes.

New techniques for more accurate unsupervised segmentation of lung tissues from Low Dose Computed Tomography (LDCT) are proposed. In this paper we describe LDCT images and desired maps of regions (lung and the other chest tissues) by a joint Markov-Gibbs random field model (MGRF) of independent image signals and interdependent region labels but focus on most accurate model identification. To better specify region borders, each empirical distribution of signals is precisely approximated by a Linear Combination of Discrete Gaussians (LCDG) with positive and negative components. We modify a conventional Expectation-Maximization (EM) algorithm to deal with the LCDG and develop a sequential EM-based technique to get an initial LCDG-approximation for the modified EM algorithm. The initial segmentation based on the LCDG-models is then iteratively refined using a MGRF model with analytically estimated potentials. Experiments on real data sets confirm high accuracy of the proposed approach. 1

We propose a novel parametric deformable model controlled by shape and visual appearance priors learned from a training subset of co-aligned images of goal objects. The shape prior is derived from a linear combination of vectors of distances between the training boundaries and their common centroid. The appearance prior considers gray levels within each training boundary as a sample of a Markov-Gibbs random field with pairwise interaction. Spatially homogeneous interaction geometry and Gibbs potentials are analytically estimated from the training data. To accurately separate a goal object from an arbitrary background, empirical marginal gray level distributions inside and outside of the boundary are modeled with adaptive linear combinations of discrete Gaussians (LCDG). The evolution of the parametric deformable model is based on solving an Eikonal partial differential equation with a new speed function which combines the prior shape, prior appearance, and current appearance models. Due to the analytical shape and appearance priors and a simple Expectation-Maximization procedure for getting the object and background LCDG, our segmentation is considerably faster than most of the known geometric and parametric models. Experiments with various goal images confirm the robustness, accuracy, and speed of our approach.

A new approach to align an image of a textured object with a given prototype (learned reference object) is proposed. Visual appearance of the images, after equalizing their signals, is modeled with a Markov-Gibbs random field with pairwise interaction. Similarity to the prototype (learned reference object) is measured by a Gibbs energy of signal co-occurrences in a characteristic subset of pixel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by gradient search. To get accurate appearance model, we developed a new approach to automatically select the most important cliques (neighborhood system) that describe the visual appearance of a texture object. Experiments confirm that our approach aligns complex objects better than popular conventional algorithms.

The importance of accurate early diagnosis of dyslexia, which severely affects the learning abilities of children, cannot be overstated. Neuropathological studies have revealed an abnormal anatomy of the cerebral white matter (CWM) in dyslexic brains. We explore a possibility of distinguishing between dyslexic and normal (control) brains by a quantitative shape analysis of CWM gyrifications on 3D magnetic resonance (MR) images. Our approach consists of (i) segmentation of the CWM on a 3D brain image using a deformable 3D boundary; (ii) extraction of gyrifications from the segmented CWM, and (iii) shape analysis to quantify thickness of the extracted gyrifications and classify dyslexic and normal subjects. The boundary evolution is controlled by two probabilistic models of visual appearance of 3D CWM: the learned prior and the current appearance model. Initial experimental results suggest that the proposed 3D texture analysis is a promising supplement to the current techniques for diagnosing dyslexia.

Acute renal rejection is the most common reason for graft (transplanted kidney) failure after kidney transplantation, and early detection is crucial to survival of function in the transplanted kidney. The current techniques for early detection of acute renal rejection are not accurate. For example, clearances of inulin and DTPA require multiple blood and urine tests, and they provide information on both kidneys together, but not unilateral information. Moreover, biopsy (the gold standard for diagnosis of acute renal rejection after renal transplantation) could cause bleeding and infection. Also, the relatively small needle biopsies may lead to over- or underestimation of the extent of inflammation in the entire graft. Hence, a noninvasive and repeatable technique would not only be useful but is needed to ensure survival of transplanted kidneys. For this reason, we introduced a new non-invasive framework for automatic classification of normal and acute renal rejection transplants using Dynamic Contrast Enhanced Magnetic Resonance Images (DCE-MRI). In this paper, we introduce a new approach for the automatic classification of normal and acute rejection transplants from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI). The proposed algorithm consists of three main steps; the first step isolates the kidney from the surrounding anatomical structures. In the second step, new motion correction models are employed to account for both the global and local motion of the kidney due to patient moving and breathing. Finally, the perfusion curves that show the transportation of the contrast agent into the tissue are obtained from the kidney and used in the classification of normal and acute rejection transplants. In this paper, we will focus on the second and third steps and the first step is shown in detail in [1].

The importance of accurate early diagnostics of dyslexia that severely affects the learning abilities of children cannot be overstated. Neuropathological studies have revealed an abnormal anatomy of the cerebral white matter (CWM) in dyslexic brains. We explore a possibility of distinguishing between dyslexic and normal (control) brains by a quantitative shape analysis of CWM gyrifications on 3D Magnetic Resonance (MR) images. Our approach consists of (i) segmentation of the CWM on a 3D brain image using a deformable 3D boundary; (ii) extraction of gyrifications from the segmented CWM, and (iii) shape analysis to quantify thickness of the extracted gyrifications and classify dyslexic and normal subjects. The boundary evolution is controlled by two probabilistic models of visual appearance of 3D CWM: the learned prior and the current appearance model. Initial experimental results suggest that the proposed 3D texture analysis is a promising supplement to the current techniques for diagnosing dyslexia.

Acute renal rejection is the most common reason for graft (transplanted kidney) failure after kidney transplantation, and early detection is crucial to survival of function in the transplanted kidney. The current techniques for early detection of acute renal rejection are not accurate. For example, clearances of inulin and DTPA require multiple blood and urine tests, and they provide information on both kidneys together, but not unilateral information. Moreover, biopsy (the gold standard for diagnosis of acute renal rejection after renal transplantation) could cause bleeding and infection. Also, the relatively small needle biopsies may lead to over- or underestimation of the extent of inflammation in the entire graft. Hence, a noninvasive and repeatable technique would not only be useful but is needed to ensure survival of transplanted kidneys. For this reason, we introduced a new non-invasive framework for automatic classification of normal and acute renal rejection transplants using dynamic contrast enhanced magnetic resonance images (DCE-MRI). In this paper, we introduce a new approach for the automatic classification of normal and acute rejection transplants from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI). The proposed algorithm consists of three main steps; the first step isolates the kidney from the surrounding anatomical structures. In the second step, new motion correction models are employed to account for both the global and local motion of the kidney due to patient moving and breathing. Finally, the perfusion curves that show the transportation of the contrast agent into the tissue are obtained from the kidney and used in the classification of normal and acute rejection transplants. In this paper, we will focus on the second and third steps and the first step is shown in detail by A. El-Baz et al (2005).

Our long term research goal is to develop a fully automated, image-based diagnostic system for early diagnosis of pulmonary nodules that may lead to lung cancer. This paper focuses on monitoring the development of lung nodules detected in successive chest low dose (LD) CT scans of a patient. We propose a new methodology for 3D LDCT data registration which is non-rigid and involves two steps: (i) global alignment of one scan (target) to another scan (reference or prototype) using the learned prior appearance model followed by (ii) local alignment in order to correct for intricate deformations. After equalizing signals for two subsequent chest scans, visual appearance of these chest images is modeled with a Markov-Gibbs random field with pairwise interaction. We estimate the affine transformation that globally register the target to the prototype by gradient descent maximization of a special Gibbs energy function. To handle local deformations, we deform each voxel of the target over evolving closed equi-spaced surfaces (iso-surfaces) to closely match the prototype. The evolution of the iso-surfaces is guided by an exponential speed function in the directions that minimize distances between the corresponding voxel pairs on the iso-surfaces in both the data sets. Preliminary results on the 135 LDCT data sets from 27 patients show that our proper registration could lead to precise diagnosis and identification of the development of the detected pulmonary nodules.

Abstract. A new approach to align an image of a textured object with a given prototype is proposed. Visual appearance of the images, after equalizing their signals, is modeled with a Markov-Gibbs random field with pairwise interaction. Similarity to the prototype is measured by a Gibbs energy of signal co-occurrences in a characteristic subset of pixel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by gradient search. Experiments confirm that our approach aligns complex 2D/3D objects better than popular conventional algorithms. 1

We propose novel expectation maximization (EM) based algorithms for accurate approximation of an empirical probability distribution of discrete scalar data. The algorithms refine our previous ones in that they approximate the empirical distribution with a linear combination of discrete Gaussians (LCDG). The use of the DGs results in closer approximation and considerably better convergence to a local likelihood maximum compared to previously involved conventional continuous Gaussian densities. Experiments in segmenting multimodal medical images show the proposed algorithms produce more adequate region borders.

A pulmonary nodule is the most common manifestation of lung cancer. Lung nodules are approximately-spherical regions of relatively high density that are visible in X-ray images of the lung. Large (generally defined as greater than 1 cm in diameter) malignant nodules can be easily detected with traditional imaging equipment and can be diagnosed by needle biopsy or bronchoscopy techniques. However, the diagnostic options for small malignant nodules are limited due to problems associated with accessing small tumors, especially if they are located deep in the tissue or away from the large airways; therefore, additional diagnostic and imaging techniques are needed. One of the most promising techniques for detecting small cancerous nodules relies on characterizing the nodule based on its growth rate. The growth rate is estimated by measuring the volumetric change of the detected lung nodules over time, so it is important to accurately measure the volume of the nodules to quantify their growth rate over time. In this paper, we introduce a novel Computer Assisted Diagnosis (CAD) system for early diagnosis of lung cancer. The proposed CAD system consists of five main steps. These steps are: (i) segmentation of lung tissues from low dose computed tomography (LDCT) images, (ii) detection of lung nodules from segmented lung tissues, (iii) a non-rigid registration approach to align two successive LDCT scans and to correct the motion artifacts caused by breathing and patient motion, (iv) segmentation of the detected lung nodules, and (v) quantification of the volumetric changes. Our preliminary classification results based on the analysis of the growth rate of both benign and malignant nodules for 10 patients (6 patients diagnosed as malignant and 4 diagnosed as benign) were 100% for 95% confidence interval. The preliminary results of the proposed image analysis have yielded promising results that would supplement the use of current technologies for diagnosing lung cancer.

Our long term research goal is to develop an image-based approach for early diagnosis of lung nodules that may lead to lung cancer. This paper focuses on monitoring the progress of detected lung nodules in successive chest low dose CT (LDCT) scans of a patient using non-rigid registration. In this paper, we propose a new methodology for 3D LDCT data registration. The registration methodology is non-rigid and involves two steps: global alignment of one scan (target data) to another scan (reference data) using the learned prior appearance model followed by local alignments in order to correct for intricate deformations. From two subsequent chest scans, visual appearance of the chest images, after equalizing their signals, are modeled with a Markov-Gibbs random field with pairwise interaction. Our approach is based on finding the affine transformation to register one data set (target data) to another data set (reference data) by maximizing a special Gibbs energy function using a gradient descent algorithm. To get accurate appearance model, we developed a new approach to an automatically select the most important cliques that describe the visual appearance of LDCT data. To handle local deformations, we propose a new approach based on deforming each voxel over evolving closed and equi-spaced surfaces (iso-surfaces) to closely match the prototype. The evolution of the iso-surfaces is guided by an exponential speed function in the directions minimizing distances between corresponding pixel pairs on the iso-surfaces on both data sets. Our preliminary results on 10 patients show that the proper registration could lead to precise identification of the progress of the detected lung nodules.

A new approach to align an image of a textured object with a given prototype is proposed. Visual appearance of the images, after equalizing their signals, is modeled with a Markov-Gibbs random field with pairwise interaction. Similarity to the prototype is measured by a Gibbs energy of signal cooccurrences in a characteristic subset of pixel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by gradient search. Experiments confirm that our approach aligns complex objects better than popular conventional algorithms.

A new physically justified adaptive probabilistic model of blood vessels on magnetic resonance angiography (MRA) images is proposed. The model accounts for both laminar (for normal subjects) and turbulent blood flow (in abnormal cases like anemia or stenosis) and results in a fast algorithm for extracting a 3D cerebrovascular system from the MRA data. Experiments with real data sets confirm the high accuracy of the proposed approach.

We propose new techniques for unsupervised segmentation of multimodal grayscale images such that each region-of-interest relates to a single dominant mode of the empirical marginal probability distribution of grey levels. We follow the most conventional approaches in that initial images and desired maps of regions are described by a joint Markov-Gibbs random field (MGRF) model of independent image signals and interdependent region labels. However, our focus is on more accurate model identification. To better specify region borders, each empirical distribution of image signals is precisely approximated by a linear combination of Gaussians (LCG) with positive and negative components. We modify an expectation-maximization (EM) algorithm to deal with the LCGs and also propose a novel EM-based sequential technique to get a close initial LCG approximation with which the modified EM algorithm should start. The proposed technique identifies individual LCG models in a mixed empirical distribution, including the number of positive and negative Gaussians. Initial segmentation based on the LCG models is then iteratively refined by using the MGRF with analytically estimated potentials. The convergence of the overall segmentation algorithm at each stage is discussed. Experiments show that the developed techniques segment different types of complex multimodal medical images more accurately than other known algorithms.

Deformable or active contour, and surface models are powerful image segmentation techniques. We introduce a novel fast and robust bi-directional parametric deformable model which is able to segment regions of intricate shape in multi-modal greyscale images. The power of the algorithm in terms of computation time and robustness is owing to the use of joint probabilities of the signals and region labels in individual points as external forces guiding the model evolution. These joint probabilities are derived from a Markov– Gibbs random field (MGRF) image model considering an image as a sample of two interrelated spatial stochastic processes. The low level process with conditionally independent and arbitrarily distributed signals relates to the observed image whereas its hidden map of regions is represented with the high level MGRF of interdependent region labels. Marginal probability distributions of signals in each region are recovered from a mixed empirical signal distribution over the whole image. In so doing, each marginal is approximated with a linear combination of Gaussians (LCG) having both positive and negative components. The LCG parameters are estimated using our previously proposed modification of the EM algorithm, and the high-level Gibbs potentials are computed analytically. Comparative experiments show that the proposed model outlines complicated boundaries of different modal objects much more accurately than other known counterparts. 1

A complete framework is proposed for applying the maximum a posteriori (MAP) estimation principle in remote sensing image segmentation. The MAP principle provides an estimate for the segmented image by maximizing the posterior probabilities of the classes defined in the image. The posterior probability can be represented as the product of the class conditional probability (CCP) and the class prior probability (CPP). In this paper, novel supervised algorithms for the CCP and the CPP estimations are proposed which are appropriate for remote sensing images where the estimation process might to be done in high-dimensional spaces. For the CCP, a supervised algorithm which uses the support vector machines (SVM) density estimation approach is proposed. This algorithm uses a novel learning procedure, derived from the main field theory, which avoids the (hard) quadratic optimization problem arising from the traditional formulation of the SVM density estimation. For the CPP estimation, Markov random field (MRF) is a common choice which incorporates contextual and geometrical information in the estimation process. Instead of using predefined values for the parameters of the MRF, an analytical algorithm is proposed which automatically identifies the values of the MRF parameters. The proposed framework is built in an iterative setup which refines the estimated image to get the optimum solution. Experiments using both synthetic and real remote sensing data (multispectral and hyperspectral) show the powerful performance of the proposed framework. The results show that the proposed density estimation algorithm outperforms other algorithms for remote sensing data over a wide range of spectral dimensions. The MRF modeling raises the segmentation accuracy by up to 10% in remote sensing images.

In this paper, we propose a novel algorithm for isolating lung abnormalities (nodules) from low dose spiral chest CT scans. The proposed algorithm consists of three main steps. The first step isolates the lung nodules, arteries, veins, bronchi, and bronchioles from the surrounding anatomical structures. The second step detects lung nodules using deformable 2D and 3D templates describing typical geometry and gray level distribution within the nodules of the same type. The detection combines the normalized cross-correlation template matching and genetic optimization algorithm. The final step eliminates the false positive nodules (FPNs) using three features that robustly define the true lung nodules. Accurate density estimation for these three features is obtained using logistic regression model and linear combination of Gaussians (LCG) with positive and negative components. This paper focuses on the second and third steps. Experiments with 200 patients' CT scans demonstrate the accuracy of our approach.

Our aim is to develop a fully automatic computer-assisted diagnosis (CAD) system for lung cancer screening using chest spiral CT scans. A screening program on 1000 subjects aims at quantification of the effectiveness of low dose spiral CT scans for early diagnosis of lung cancer, and evaluation of its possible impact on improving the mortality rate of cancer patients. The paper presents an image analysis system for 3D reconstruction of the lungs and trachea, detection of lung abnormalities, identification/classification of these abnormalities with respect to specific diagnosis, and distributed visualization of the results over computer networks. We present two novel approaches for segmentation of the lung tissues from the surrounding structures in the chest cavity, and detection of abnormalities in the lungs. The segmentation algorithm is hierarchical, first isolating the background from the chest cavity, then isolating the lungs from surrounding structures (e.g., ribs, liver, and other organs). Abnormalities in the lungs are detected by analyzing the segmented lung tissues and extracting the isolated lumps that appear in various connected regions. 3D reconstructions are also generated for these abnormalities, to be used for subsequent identification/classification steps. Results on 50 subjects are shown, and have been evaluated against radiologists. Our image analysis approach has provided comparable results with respect to the experts. The approach is quite fast, and lends itself to distributed visualization over computer networks.

Stochastic models of images are commonly represented in terms of three random processes (random fields) defined on the region of support of the image. The observed image process G is considered as a composite of two random process: a high level process G/sup h/, which represents the regions (or classes) that form the observed image; and a low level process G/sup l/, which describes the statistical characteristics of each region (or class). The representation G = (G/sup h/, G/sup l/) has been widely used in the image processing literature in the past two decades. In this paper, we consider the low level process G/sup l/ as mixture of normal distributions, and we use the expectation-maximization (EM) algorithm to estimate the mean, the variance, and proportion for each distribution. A popular model for the high level process G/sup h/ has been the Gibbs-Markov random field (GMRF) model. We introduce a novel unsupervised approach to estimate the parameters of a GMRF model. In this approach, we estimate the model parameters that maximize the posteriori probability of each pixel in a given image. The MAP estimate is obtained using a combination of genetic search and deterministic optimization using the iterated conditional mode (ICM) approach of Besag. The desired estimate of the GMRF parameters is the one corresponding to the MAP estimate. The approach has been applied on real images (Spiral CT slices) and provides satisfactory results.

With the growing interest in current-mode analogue circuits, this paper introduce an implementation of the second generation current conveyor using CMOS transistors and bipolar junction transistors in order to take the advantages of each one. Circuit details are given and simulation results are shown. The proposed circuit is suitable for implementation using a 0.8 /spl mu/m BiCMOS process technology. Results indicate that the bandwidth for both the voltage mode and the current mode operation exceed 1 GHz.