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.

Effective medication management is crucial for improving treatment outcomes, particularly among the elderly and those with chronic conditions. To mitigate the risks associated with poor medication management, this paper proposes an artificial intelligence-based medical dispenser system. The proposed system addresses the limitations of existing pill dispenser systems through medical paper digitization and an adaptable pick-and-drop dispensing system capable of accommodating pills with different shapes, textures, and sizes. Our methodology initially involved developing a computer vision algorithm to identify key details in medical prescriptions, such as medication dosage and frequency. The image data was then converted into textual data frames for further analysis using a large language model. Subsequently, we designed a suction-based pill dispensing unit with a linear actuator and an air pump motor, picking up pills from compartments on a tray controlled by a stepper motor. Our proposed digitization algorithm achieved an average intersection over the union score of 0.952 in detecting regions of interest in medical prescriptions with optical character recognition yielding average word and character error rates of 0.039 and 0.025, respectively. The employment of OpenAI’s language model demonstrates efficacy in error parsong, resolving 52.63% of the optical character recognition errors. The pill dispensing mechanism effectively extracts pills of different sizes and shapes, and the rotating tray mechanism aligns in the respective dispensing and collection locations precisely with a success rate of 100% in placing the containers in the required locations. Overall, the results are promising, suggesting that the proposed system may pave the way for more generalized, intelligent medication management solutions.

Retinopathy is a group of retinal disabilities that causes severe visual impairments or complete blindness. Due to the capability of optical coherence tomography to reveal early retinal abnormalities, many researchers have utilized it to develop autonomous retinal screening systems. However, to the best of our knowledge, most of these systems rely only on mathematical features, which might not be helpful to clinicians since they do not encompass the clinical manifestations of screening the underlying diseases. Such clinical manifestations are critically important to be considered within the autonomous screening systems to match the grading of ophthalmologists within the clinical settings. To overcome these limitations, we present a novel framework that exploits the fusion of vision language correlation between the retinal imagery and the set of clinical prompts to recognize the different types of retinal disabilities. The proposed framework is rigorously tested on six public datasets, where, across each dataset, the proposed framework outperformed state-of-the-art methods in various metrics. Moreover, the clinical significance of the proposed framework is also tested under strict blind testing experiments, where the proposed system achieved a statistically significant correlation coefficient of 0.9185 and 0.9529 with the two expert clinicians. These blind test experiments highlight the potential of the proposed framework to be deployed in the real world for accurate screening of retinal diseases.

This study presents a performance comparison of different deep machine learning models for the intelligent segregation of date fruit bunches of numerous varieties. The shape, size, and color of the various types of dates with different maturity conditions require experienced farmers to estimate the accrual class. This study has used a transfer learning approach on various machine learning models (VGG-19, MobileNetV2, DenseNet, and NASNet) to classify five different kinds of date bunches (Barhi, Khalas, Menifi, Nabout saif, and Sullaj). Each model is trained on a dataset of 11,944 images of five different date classes. The comparison deduces that DenseNet produces the best accuracy, precision, and recall when compared with the performance of other models. The maximum achieved accuracy of the trained DenseNet model is $100 \%$ for the validation dataset and 98.4% for the test dataset.

This paper presents a thorough review of recent advancements in screening heart and lung diseases via auscultation using artificial intelligence (AI) methods. Auscultation has historically been fundamental in diagnosing cardiopulmonary conditions; however, conventional techniques depend significantly on clinician proficiency, rendering diagnosis vulnerable to human error. Recent advancements in digital stethoscopes and AI-based sound analysis algorithms have transformed the conventional analysis, facilitating more precise, real-time identification of anomalies such as murmurs, arrhythmias, wheezes, and crackles. This paper delineates the principal methodologies employed in sound acquisition, feature extraction, and disease classification, while assessing the reliability of diverse models of machine learning and deep learning. Moreover, the paper addresses the obstacles in implementing these technologies in clinical practice, including data standardization, computational constraints, and integration with current healthcare systems. The results indicate that AI-augmented stethoscope systems have significant potential to enhance early diagnosis and patient outcomes for cardiac and pulmonary conditions.

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.

This work proposes a flexible, foldable, lightweight, robust, and smart cane to aid visually impaired individuals and patients in navigating unfamiliar environments safely. The developed smart cane is equipped with an ultrasonic sensor, RFID reader, and an AI machine vision sensor for object detection and identification in the range of 30 cm to 9 m. A mobile application with a text-to-voice feature is developed that connects with the cane using Bluetooth to provide voice warnings to the user based on processed sensor output. The developed cane is also equipped with a vibration sensor activated when an obstacle is closer than 30 cm, serving as a backup of voice warnings. Object detection and classification using multiple sources (AI vision sensor, ultrasonic sensor, and RFID readers) ensures robust and uninterrupted operation in case of failure of one sensor. In emergencies, users can send text messages with their location to a pre-selected caretaker’s phone number using the installed SOS button. The rechargeable battery offers more than 24 hours of operation and warns users when the battery is low. The prototype has been successfully executed and tested in various environments and aims to improve the safety and quality of life for visually impaired individuals and hospital patients.

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.

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.

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.

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.

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.

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%.

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 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.

One of the most recent advances in navigation systems is incorporating panoramic views. In this paper, we propose a mobile-edge computing (MEC) network architecture for presenting mobile end users with panoramic videos of the trip between two selected map locations with an improved quality of service compared to traditional networks. Our panoramic videos comprise of crowd-sourced recordings of various locations for cost reduction or centrally collected videos for more uniform quality. To synthesise quality panoramic videos of the path, we propose integrating video quality assessment, speed-adaptive frame-rates adjustment, and video segment merging based on the Dijkstra algorithm. We also consider other attributes such as the time and spatial coordinates at which the videos are captured, the overlap of spatial coverage, and the prediction of optimal base station for panoramic video delivery. We utilise a MEC architecture because our application requires a network with high-bandwidth and low-latency, which calls for the integration of technologies at the edge of the network. Part of our algorithm and our video database are replicated and migrated to the edge of mobile networks allowing us to use base stations as more than mere mobile access points.

In this paper, we propose an integrated caregiver-focused framework that aims to provide a health care and a fall detection service for elderly users. The proposed system looks at the responsibility of the elder-care from three different perspectives: maintenance of an accurate and updated health history, prevention of inappropriate dietary options, and detection of major fall accidents. We ensure a timely intervention by capitalizing on smart watches and their ability to notify the caregiver any time and anywhere. The integrated system provides the users with an organized medical journal that gives an insight of their medical status while being able to share it with their doctor Moreover, the system provides a food and nutrition guide that allows the users to evaluate their food intake both quantity and quality wise. Lastly, users can benefit from a fall detection service that uses the sensors available on the commercial smart watches and the cascade feed-forward neural network for classification. The experiments performed result in an accuracy of 93.33% of the proposed system in the classification of fall events.

This paper proposes a method for localizing homogeneity and estimating additive white Gaussian noise (AWGN) variance in images. The proposed method uses spatially and sparsely scattered initial seeds and utilizes particle filtering techniques to guide their spatial movement towards homogeneous locations. This way, the proposed method avoids the need to perform the full search associated with block-based noise estimation methods. To achieve this, the paper proposes for the particle filter a dynamic model and a homogeneity observation model based on Laplacian structure detectors. The variance of AWGN is robustly estimated from the variances of blocks in the detected homogeneous areas. A proposed adaptive trimmed-mean based robust estimator is used to account for the reduction in estimation samples from the full search approach. Our results show that the proposed method reduces the number of homogeneity measurements required by block-based methods while achieving more accuracy.

In this letter, we propose a structure-oriented multidirectional Wiener filter to reduce additive white Gaussian noise in image and video signals. A local activity profile based on second derivatives is used to restrict filtering to homogeneous directions to combat blurring. The proposed filter improves the Wiener estimate of denoised pixels to reduce the residual blurring of the conventional Wiener filter while achieving higher noise-reduction gains of up to 5.6 dB peak signal-to-noise-ratio (PSNR). The parameters of the proposed filter (block size, shape and coefficients) are adapted to image structure and noise level for optimization with respect to noise-reduction gain and structure preservation. The effectiveness of the proposed method is shown using both the PSNR and the modulation transfer function calculated for a range of spatial frequencies to measure the degradation in contrast due to blurring. Our results show that the proposed method achieves a higher contrast transfer ratio than the conventional Wiener filter indicating improved preservation of high frequency content. We also show the performance of the proposed filter relative to reference anisotropic diffusion and wavelet methods.

Most global motion estimation (GME) methods are oriented to video coding while video object segmentation methods either assume no global motion (GM) or directly adopt a coding-oriented method to compensate for GM. This paper proposes a hierarchical differential GME method oriented to video object segmentation. A scheme which combines three-step search and motion parameters prediction is proposed for initial estimation to increase efficiency. A robust estimator that uses object information to reject outliers introduced by local motion is also proposed. For the first frame, when the object information is unavailable, a robust estimator is proposed which rejects outliers by examining their distribution in local neighborhoods of the error between the current and the motion-compensated previous frame. Subjective and objective results show that the proposed method is more robust, more oriented to video object segmentation, and faster than the referenced methods.

This paper proposes a method to integrate motion and region information into a recursive temporal noise reduction filter for video signals. We also propose an artifact-robust motion detection algorithm suitable for noise reduction. It is based on local low-pass and maximum filters and on noise-adaptive global gray-level stabilization. Region information is obtained from difference frames resulting from the proposed motion detection. The detected motion and regions are then integrated to compute the temporal filter coefficients that reduce both noise and motion blur. Simulation results show that the proposed method increases the performance of recursive temporal filtering and achieves an average gain of 3.6 dB.

This paper proposes a method which utilizes invariant wavelet features for correcting total occlusion in video surveillance applications. The proposed method extracts invariant wavelet features from the pre-occlusion spatial image of disappearing objects. When new objects are detected during occlusion, their extracted invariant wavelet features are compared to those of lost objects to check for reappearance. When reappearance occurs, the proposed method rebuilds the correct correspondence map between pre-occlusion and post occlusion objects to continue to track the ones that were lost during total occlusion. Our results show that the proposed method is more robust than referenced methods especially when objects change or reverse their motion direction during occlusion.

This paper proposes a method for the realtime detection of vandalism in video sequences. The proposed method detects vandalism through the robust extraction of a sequence of high-level events leading to it without resorting to object recognition and using a single camera. Vandalism is declared when an object enters the scene and causes an unauthorized change inside a predefined vandalisable area in the scene such as a pay phone or a sign. The proposed method was tested offline and on-line and our results show that it is robust in detecting vandalism or graffiti in surveillance video sequences.

This paper proposes a novel algorithm for the real-time detection and correction of occlusion and split in feature-based tracking of objects for surveillance applications. The proposed algorithm detects sudden variations of spatio-temporal features of objects in order to identify possible occlusion or split events. The detection is followed by a validation stage that uses past tracking information to prevent false detection of occlusion or split. Special care is taken in case of heavy occlusion, when there is a large superposition of objects. In this case the system relies on long-term temporal behavior of objects to avoid updating the video object features with unreliable (e.g. shape and motion) information. Occlusion is corrected by separating occluded objects. For the detection of splits, in addition to the analysis of spatio-temporal changes in objects features, our algorithm analyzes the temporal behavior of split objects to discriminate between errors in segmentation and real separation of objects, such as in the deposit of an object. Split is corrected by physically merging the objects detected to be split. To validate the proposed approach, objective and visual results are presented. Experimental results show the ability of the proposed algorithm to detect and correct, both, split and occlusion of objects. The proposed algorithm is most suitable in video surveillance applications due to: its good performance in multiple, heavy, and total occlusion; its distinction between real object separation and faulty object split; its handling of simultaneous occlusion and split events; and its low computational complexity.

This paper proposes a spatio-temporal technique for estimating the noise variance in noisy video signals, where the noise is assumed to be additive white Gaussian noise. The proposed technique utilizes domain-wise (spatial, temporal, and spatio-temporal) video information independently for improved reliability. It divides the video signal into cubes and measures their homogeneity using Laplacian of Gaussian based operators. Then, the variances of homogeneous cubes are selected to estimate the noise variance. A least median of squares robust estimator is used to reject outliers and produce domain-wise noise variance estimates which are adaptively integrated to obtain the final frame-wise estimate. The proposed technique estimates the noise variance reliably in video sequences with both low and high video activities (e.g., fast motion or high spatial structure) and it produces a maximum estimation error of 1.7-dB peak signal-to-noise ratio. The proposed method is fast when compared to referenced methods.

Noise can highly impact the performance of video processing algorithms. This paper proposes a new real-time spatio-temporal method for estimating the noise variance in video signals. The proposed algorithm selects 3D regions or cubes in the video signal with high intensity uniformity. The noise variance is estimated from the selected set of spatially, temporally and spatio-temporally intensity-uniform cubes using local variances calculated along homogeneous plains. The proposed algorithm works well for sequences with high structure and motion activity and outperforms other methods with a worst-case estimation error of 2 dB. It works well for highly noisy and non-noisy sequences

This paper proposes a method for the reduction of white Gaussian video noise. The method achieves a maximum gain of 5.6 dB and is capable of preserving image content. It adapts window size, weighting and behavior to both image content and noise level in order to optimize the filtering. It starts by detecting the intensity-homogeneous direction from 8 different candidates. A variant of the Wiener filter is then applied directionally. The filtering is performed along homogeneous areas and not across edges. For noisy images, the filtering is increased automatically by using a larger kernel size. The proposed filter achieves better image preservation by turning off gradually for less noisy images. It works well for both highly noisy and good-quality images

This paper proposes a real-time method for the reduction of white Gaussian video noise. The method achieves a maximum gain of 4.8 dB and is capable of preserving image content. It adapts window size, weighting and behavior to both image content and noise level in order to optimize the filtering. It starts by detecting the intensity-homogeneous direction from 8 different candidates. A variant of the sigma filter is then applied directionally. The filtering is performed along homogeneous areas and not across edges. For noisy images, the filtering is increased automatically by using the two most homogeneous directions with a larger kernel size. The proposed filter achieves better image preservation by turning off gradually for less noisy images. It works well for both highly noisy and good-quality images without the introduction of speed or hardware implementation challenges.