Over the past few years, artificial intelligence (AI) has emerged as a transformative force in drug discovery and development (DDD), revolutionizing many aspects of the process. This survey provides a comprehensive review of recent advancements in AI applications within early drug discovery and post-market drug assessment. It addresses the identification and prioritization of new therapeutic targets, prediction of drug-target interaction (DTI), design of novel drug-like molecules, and assessment of the clinical efficacy of new medications. By integrating AI technologies, pharmaceutical companies can accelerate the discovery of new treatments, enhance the precision of drug development, and bring more effective therapies to market. This shift represents a significant move towards more efficient and cost-effective methodologies in the DDD landscape.

The extensive adoption of artificial intelligence in clinical decision support systems requires greater model interpretability. Hence, we introduce EvolveFNN, an interpretable model based on the recurrent neural network that merges fuzzy logic principles with recurrent units. This model is designed to train precise and understandable models using high-dimensional longitudinal electronic health records data. Through supervised learning, our method allows the identification of variable encoding functions and significant rules. To demonstrate performance and capabilities in classification and rule discovery, we first test our method on a simulated dataset. The proposed methods achieve the best model performance compared to other methods, and the rules learned are almost identical to what we used to generate the synthetic data. Furthermore, we showcase a pilot application that proves its potential in the early detection of cardiac event onset. Our proposed algorithm obtains a comparable model performance to vanilla GRU models and remains relatively stable when the prediction window size changes. Examining the rules generated by our proposed model, we find that the extracted rules not only align with clinical practices and existing literature but also provide potential risk factors not explored in the population. The additional experiments on the MIMIC-III benchmark dataset show the algorithm's generalizability. In conclusion, our proposed approach can effectively train accurate, interpretable, and reliable models using large longitudinal electronic health records, offering clinicians valuable insights.

The advanced learning paradigm, learning using privileged information (LUPI), leverages information in training that is not present at the time of prediction. In this study, we developed privileged logistic regression (PLR) models under the LUPI paradigm to detect acute respiratory distress syndrome (ARDS), with mechanical ventilation variables or chest x-ray image features employed in the privileged domain and electronic health records in the base domain. In model training, the objective of privileged logistic regression was designed to incorporate data from the privileged domain and encourage knowledge transfer across the privileged and base domains. An asymptotic analysis was also performed, yielding sufficient conditions under which the addition of privileged information increases the rate of convergence in the proposed model. Results for ARDS detection show that PLR models achieve better classification performances than logistic regression models trained solely on the base domain, even when privileged information is partially available. Furthermore, PLR models demonstrate performance on par with or superior to state-of-the-art models under the LUPI paradigm. As the proposed models are effective, easy to interpret, and highly explainable, they are ideal for other clinical applications where privileged information is at least partially available.

A model's interpretability is essential to many practical applications such as clinical decision support systems. In this article, a novel interpretable machine learning method is presented, which can model the relationship between input variables and responses in humanly understandable rules. The method is built by applying tropical geometry to fuzzy inference systems, wherein variable encoding functions and salient rules can be discovered by supervised learning. Experiments using synthetic datasets were conducted to demonstrate the performance and capacity of the proposed algorithm in classification and rule discovery. Furthermore, we present a pilot application in identifying heart failure patients that are eligible for advanced therapies as proof of principle. From our results on this particular application, the proposed network achieves the highest F1 score. The network is capable of learning rules that can be interpreted and used by clinical providers. In addition, existing fuzzy domain knowledge can be easily transferred into the network and facilitate model training. In our application, with the existing knowledge, the F1 score was improved by over 5%. The characteristics of the proposed network make it promising in applications requiring model reliability and justification.

Patients recovering from cardiovascular surgeries may develop life-threatening complications such as hemodynamic decompensation, making the monitoring of patients for such complications an essential component of postoperative care. However, this need has given rise to an inexorable increase in the number and modalities of data points collected, making it challenging to effectively analyze in real time. While many algorithms exist to assist in monitoring these patients, they often lack accuracy and specificity, leading to alarm fatigue among healthcare practitioners. In this study we propose a multimodal approach that incorporates salient physiological signals and EHR data to predict the onset of hemodynamic decompensation. A retrospective dataset of patients recovering from cardiac surgery was created and used to train predictive models. Advanced signal processing techniques were employed to extract complex features from physiological waveforms, while a novel tensor-based dimensionality reduction method was used to reduce the size of the feature space. These methods were evaluated for predicting the onset of decompensation at varying time intervals, ranging from a half-hour to 12 h prior to a decompensation event. The best performing models achieved AUCs of 0.87 and 0.80 for the half-hour and 12-h intervals respectively. These analyses evince that a multimodal approach can be used to develop clinical decision support systems that predict adverse events several hours in advance.

Predicting the interactions between drugs and targets plays an important role in the process of new drug discovery, drug repurposing (also known as drug repositioning). There is a need to develop novel and efficient prediction approaches in order to avoid the costly and laborious process of determining drug-target interactions (DTIs) based on experiments alone. These computational prediction approaches should be capable of identifying the potential DTIs in a timely manner. Matrix factorization methods have been proven to be the most reliable group of methods. Here, we first propose a matrix factorization-based method termed 'Coupled Matrix-Matrix Completion' (CMMC). Next, in order to utilize more comprehensive information provided in different databases and incorporate multiple types of scores for drug-drug similarities and target-target relationship, we then extend CMMC to 'Coupled Tensor-Matrix Completion' (CTMC) by considering drug-drug and target-target similarity/interaction tensors. Results: Evaluation on two benchmark datasets, DrugBank and TTD, shows that CTMC outperforms the matrix-factorization-based methods: GRMF, $L_{2,1}$-GRMF, NRLMF and NRLMF$\beta $. Based on the evaluation, CMMC and CTMC outperform the above three methods in term of area under the curve, F1 score, sensitivity and specificity in a considerably shorter run time.

The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug-target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.

The first version of this article neglected to acknowledge Maryam Bagherian and Elyas Sabeti's equal contributions to the study. This has now been corrected. The publisher regrets the error.

Optical colonoscopy is an essential diagnostic and prognostic tool for many gastrointestinal diseases, including cancer screening and staging, intestinal bleeding, diarrhea, abdominal symptom evaluation, and inflammatory bowel disease assessment. However, the evaluation, classification, and quantification of findings from colonoscopy are subject to inter-observer variation. Automated assessment of colonoscopy is of interest considering the subjectivity present in qualitative human interpretations of colonoscopy findings. Localization of the camera is essential to interpreting the meaning and context of findings for diseases evaluated by colonoscopy. In this study, we propose a camera localization system to estimate the relative location of the camera and classify the colon into anatomical segments. The camera localization system begins with non-informative frame detection and removal. Then a self-training end-to-end convolutional neural network is built to estimate the camera motion, where several strategies are proposed to improve its robustness and generalization on endoscopic videos. Using the estimated camera motion a camera trajectory can be derived and a relative location index calculated. Based on the estimated location index, anatomical colon segment classification is performed by constructing a colon template. The proposed motion estimation algorithm was evaluated on an external dataset containing the ground truth for camera pose. The experimental results show that the performance of the proposed method is superior to other published methods. The relative location index estimation and anatomical region classification were further validated using colonoscopy videos collected from routine clinical practice. This validation yielded an average accuracy in classification of 0.754, which is substantially higher than the performances obtained using location indices built from other methods.

Acute respiratory distress syndrome (ARDS) is a fulminant inflammatory lung injury that develops in patients with critical illnesses, affecting 200,000 patients in the United States annually. However, a recent study suggests that most patients with ARDS are diagnosed late or missed completely and fail to receive life-saving treatments. This is primarily due to the dependency of current diagnosis criteria on chest x-ray, which is not necessarily available at the time of diagnosis. In machine learning, such an information is known as Privileged Information - information that is available at training but not at testing. However, in diagnosing ARDS, privileged information (chest x-rays) are sometimes only available for a portion of the training data. To address this issue, the Learning Using Partially Available Privileged Information (LUPAPI) paradigm is proposed. As there are multiple ways to incorporate partially available privileged information, three models built on classical SVM are described. Another complexity of diagnosing ARDS is the uncertainty in clinical interpretation of chest x-rays. To address this, the LUPAPI framework is then extended to incorporate label uncertainty, resulting in a novel and comprehensive machine learning paradigm - Learning Using Label Uncertainty and Partially Available Privileged Information (LULUPAPI). The proposed frameworks use Electronic Health Record (EHR) data as regular information, chest x-rays as partially available privileged information, and clinicians' confidence levels in ARDS diagnosis as a measure of label uncertainty. Experiments on an ARDS dataset demonstrate that both the LUPAPI and LULUPAPI models outperform SVM, with LULUPAPI performing better than LUPAPI.

Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Automated brain hematoma segmentation and outcome prediction for patients with TBI can effectively facilitate patient management. In this study, we propose a novel Multi-view convolutional neural network with a mixed loss to segment total acute hematoma on head CT scans collected within 24 h after the injury. Based on the automated segmentation, the volumetric distribution and shape characteristics of the hematoma were extracted and combined with other clinical observations to predict 6-month mortality. The proposed hematoma segmentation network achieved an average Dice coefficient of 0.697 and an intraclass correlation coefficient of 0.966 between the volumes estimated from the predicted hematoma segmentation and volumes of the annotated hematoma segmentation on the test set. Compared with other published methods, the proposed method has the most accurate segmentation performance and volume estimation. For 6-month mortality prediction, the model achieved an average area under the precision-recall curve (AUCPR) of 0.559 and area under the receiver operating characteristic curve (AUC) of 0.853 using 10-fold cross-validation on a dataset consisting of 828 patients. The average AUCPR and AUC of the proposed model are respectively more than 10% and 5% higher than those of the widely used IMPACT model.

Copy number variation (CNV) is a type of genomic/genetic variation that plays an important role in phenotypic diversity, evolution, and disease susceptibility. Next generation sequencing (NGS) technologies have created an opportunity for more accurate detection of CNVs with higher resolution. However, efficient and precise detection of CNVs remains challenging due to high levels of noise and biases, data heterogeneity, and the "big data" nature of NGS data. Sequence coverage (readcount) data are mostly used for detecting CNVs, specially for whole exome sequencing data. Readcount data are contaminated with several types of biases and noise that hinder accurate detection of CNVs. In this work, we introduce a novel preprocessing pipeline for reducing noise and biases to improve the detection accuracy of CNVs in heterogeneous NGS data, such as cancer whole exome sequencing data. We have employed several normalization methods to reduce readcount's biases that are due to GC content of reads, read alignment problems, and sample impurity. We have also developed a novel efficient and effective smoothing approach based on Taut String to reduce noise and increase CNV detection power. Using simulated and real data we showed that employing the proposed preprocessing pipeline significantly improves the accuracy of CNV detection.

Traumatic brain injury (TBI) is a major health and socioeconomic problem globally that is associated with a high level of mortality. Early and accurate diagnosis and prognosis of TBI is important in patient management and preventing any secondary injuries. Computer tomography (CT) imaging assists physicians in diagnosing injury and guiding treatment. One of the clinical parameters extracted from CT images is midline shift, a measure of linear displacement in brain structure, which is correlated with TBI patient outcomes. However, only a tiny fraction of the overall tissue displacement is quantified through this parameter. In this paper, a novel measurement of overall mid-surface shift is proposed that quantifies the total volume of brain tissue shifted across the midline. When compared to traditional midline shift, mid-surface shift has a stronger correlation with TBI patient outcomes.

Determining the appropriate timing of mechanical circulatory support (MCS) or heart transplantation (HT) for patients with advanced heart failure is essential as there may be a mortality cost to delayed care. An automated decision-making system that can identify patients eligible for a HT/MCS would facilitate primary care physicians or general cardiologists referring those patients for consideration of advanced therapies. In this study, a novel fuzzy neural network was built by integrating fuzzy set theory, neural network, and genetic algorithm techniques. The overall architecture of the proposed fuzzy neural network was inspired by clinical practice guidelines. Clinical variables were encoded using fuzzy concepts and rules were calculated in a fully-connected layer with constraints in weights. From the experiments, the proposed fuzzy neural network achieved an average AUC of 0.838 and an F1 score of 0.462. The rules from the trained network were further analyzed. Our results show that the proposed fuzzy neural network can not only achieve good classification performance, but also provides transparency with respect to knowledge extraction and interpretation.

Deep neural networks have shown great achievements in solving complex problems. However, there are fundamental challenges which limit their real world applications. Lack of a measurable criterion for estimating uncertainty of the network predictions is one of these challenges. However, we can compute the variance of the network output by applying spatial transformations, distortions or noise injection to network inputs and interpret these variances as uncertainty of the network predictions. In other words, as long as the deformations do not conceptually alter target of interest, we expect the network to produce the same result. Hence, any outputs changes can be a sign of uncertainty in the network predictions. In order to estimate the prediction uncertainty of deep convolutional neural networks we use simple random transformations. By exploiting the network uncertainty, we improve the overall performance of the system. For a real use case, we apply the proposed method to segment left ventricle in MRI cardiac images. Experimental results demonstrate state-of- the-art performance and highlight the potential capabilities of simple ideas in conjunction with deep neural networks.

Estimating scene depth from a single monocular image is a crucial component in computer vision tasks, enabling many further applications such as robot vision, 3-D modeling, and above all, 2-D to 3-D image/video conversion. Since there are an infinite number of possible world scenes, that can produce a unique image, single image depth estimation is a highly challenging task. This paper tackles such an ambiguous problem by using the merits of both global and local information (structures) of a scene. To this end, we formulate single image depth estimation as a regression problem via (on) rich depth related features which describe effective monocular cues. Exploiting the relationship between these image features and depth values is adopted via a learning model which is inspired by modified stacked generalization scheme. The experiments demonstrate competitive results compared with existing data-driven approaches in both quantitative and qualitative analysis with a remarkably simpler approach than previous works.

When training a machine learning algorithm for a supervised-learning task in some clinical applications, uncertainty in the correct labels of some patients may adversely affect the performance of the algorithm. For example, even clinical experts may have less confidence when assigning a medical diagnosis to some patients because of ambiguity in the patient's case or imperfect reliability of the diagnostic criteria. As a result, some cases used in algorithm training may be mislabeled, adversely affecting the algorithm's performance. However, experts may also be able to quantify their diagnostic uncertainty in these cases. We present a robust method implemented with support vector machines (SVM) to account for such clinical diagnostic uncertainty when training an algorithm to detect patients who develop the acute respiratory distress syndrome (ARDS). ARDS is a syndrome of the critically ill that is diagnosed using clinical criteria known to be imperfect. We represent uncertainty in the diagnosis of ARDS as a graded weight of confidence associated with each training label. We also performed a novel time-series sampling method to address the problem of intercorrelation among the longitudinal clinical data from each patient used in model training to limit overfitting. Preliminary results show that we can achieve meaningful improvement in the performance of algorithm to detect patients with ARDS on a hold-out sample, when we compare our method that accounts for the uncertainty of training labels with a conventional SVM algorithm.

Colonoscopy video frames might be contaminated by bright spots with unsaturated values known as specular reflection. Detection and removal of such reflections could enhance the quality of colonoscopy images and facilitate diagnosis procedure. In this paper, we propose a novel two-phase method for this purpose, consisting of detection and removal phases. In the detection phase, we employ both HSV and RGB color space information for segmentation of specular reflections. We first train a non-linear SVM for selecting a color space based on statistical image features extracted from each channel of the color spaces. Then, a cost function for detection of specular reflections is introduced. In the removal phase, we propose a two-step inpainting method which consists of appropriate replacement patch selection and removal of the blockiness effects. The proposed method is evaluated by testing on an available colonoscopy image database where accuracy and Dice score of 99.68% and 71.79% are achieved respectively.

Retinal vessel information is helpful in retinal disease screening and diagnosis. Retinal vessel segmentation provides useful information about vessels and can be used by physicians during intraocular surgery and retinal diagnostic operations. Convolutional neural networks (CNNs) are powerful tools for classification and segmentation of medical images. However, complexity of CNNs makes it difficult to implement them in portable devices such as binocular indirect ophthalmoscopes. In this paper a simplification approach is proposed for CNNs based on combination of quantization and pruning. Fully connected layers are quantized and convolutional layers are pruned to have a simple and efficient network structure. Experiments on images of the STARE dataset show that our simplified network is able to segment retinal vessels with acceptable accuracy and low complexity.

The need for CT scan analysis is growing for diagnosis and therapy of abdominal organs. Automatic organ segmentation of abdominal CT scan can help radiologists analyze the scans faster, and diagnose disease and injury more accurately. However, existing methods are not efficient enough to perform the segmentation process for victims of accidents and emergency situations. In this paper, we propose an efficient liver segmentation with our 3D to 2D fully convolution network (3D-2D-FCN). The segmented mask is enhanced using the conditional random field on the organ's border. Consequently, we segment a target liver in less than a minute with Dice score of 93.52%.

High-throughput next generation sequencing (NGS) technologies have created an opportunity for detecting copy number variations (CNVs) more accurately. However, efficient and precise detection of CNVs remains challenging due to high levels of noise and biases, data heterogeneity and the “big data” nature of NGS data. In this work, we introduce a novel preprocessing pipeline to improve the detection accuracy of CNVs in heterogeneous NGS data, such as cancer whole exome sequencing data. We employed several normalizations to reduce biases due to GC content, mappability and tumor contamination. We also developed a novel efficient and effective smoothing approach based on the Taut String method to reduce noise and increase the detection power of the CNV detection methods.

Traumas and illnesses can cause injury in internal organs. The liver, being the largest abdominal organ, is most likely to be injured by trauma. Currently CT scans are analyzed by radiologists to see if there is any injuries in organs; however, due to the large amounts of data and its complexity in terms of noise, intensity variations in different images and so on, visual inspection would be time consuming and prone of error. Therefore, an automated approach would be beneficial. In this paper we propose a fully automated Bayesian based method for 3D segmentation of the liver. Experimental results show that the proposed method can achieve high performance with Dice and Jaccard similarity coefficients of 93:5% and 87:9% respectively.

We propose a fast and effective method for multi-exposure image fusion. Our method blends multiple exposures under a base-detail decomposition of input images. Construction of blending weights in the proposed method is performed based on an exposedness function using luminance component of the input images. The fused base layer and detail layer are integrated into the final fused image which its detail strength is simply controlled through the integration process. Experimental results demonstrate that the proposed exposure fusion method is much faster than competing methods and can achieve state-of-the-art performance objectively and perceptually.

BACKGROUND: Transcription factors (TFs) form a complex regulatory network within the cell that is crucial to cell functioning and human health. While methods to establish where a TF binds to DNA are well established, these methods provide no information describing how TFs interact with one another when they do bind. TFs tend to bind the genome in clusters, and current methods to identify these clusters are either limited in scope, unable to detect relationships beyond motif similarity, or not applied to TF-TF interactions. METHODS: Here, we present a proximity-based graph clustering approach to identify TF clusters using either ChIP-seq or motif search data. We use TF co-occurrence to construct a filtered, normalized adjacency matrix and use the Markov Clustering Algorithm to partition the graph while maintaining TF-cluster and cluster-cluster interactions. We then apply our graph structure beyond clustering, using it to increase the accuracy of motif-based TFBS searching for an example TF. RESULTS: We show that our method produces small, manageable clusters that encapsulate many known, experimentally validated transcription factor interactions and that our method is capable of capturing interactions that motif similarity methods might miss. Our graph structure is able to significantly increase the accuracy of motif TFBS searching, demonstrating that the TF-TF connections within the graph correlate with biological TF-TF interactions. CONCLUSION: The interactions identified by our method correspond to biological reality and allow for fast exploration of TF clustering and regulatory dynamics.

The focus of this paper is motion artifact (MA) reduction from the impedance pneumography (IP) signal, which is widely used to monitor respiration. The amplitude of the MA that contaminates the IP signal is often much larger than the amplitude of the respiratory component of the signal. Moreover, the morphology and frequency composition of the artifacts may be very similar to that of the respiration, making it difficult to remove these artifacts. The proposed filter uses a regularization term to ensure that the pattern of the filtered signal is similar to that of respiration. It also ensures that the amplitude of the filter output is within the expected range of the IP signal by imposing an ε-tube on the filtered signal. The adaptive ε-tube filter is 100 times faster than the previously proposed nonadaptive version and achieves higher accuracies. Moreover, the experimental results, using several different performance measures, suggest that the proposed method outperforms popular MA reduction methods such as normalized least mean squares (NLMS) and recursive least squares (RLS) as well as independent component analysis (ICA). When used to extract the respiratory rate, the adaptive ε-tube achieves a mean error of 1.27 breaths per minute (BPM) compared to 4.72 and 4.63 BPM for the NLMS and RLS filters, respectively. When compared to the ICA algorithm, the proposed filter has an error of 1.06 BPM compared to 3.47 BPM for ICA. The statistical analyses indicate that all of the reported performance improvements are significant.

Quality assessment of stereo images confronts more challenges than its 2D counterparts. Direct use of 2D assessment methods is not sufficient to deal with the challenges of 3D perception. In this paper, an efficient general-purpose no-reference stereo image quality assessment, based on unsupervised feature learning, is presented. The proposed method extracts features without any prior knowledge about the types and levels of distortions. This property enables our method to be adaptable for different applications. The perceived contrast and phase of the binocular combination of original stereo images are utilized to learn individual dictionaries. For each distorted stereo image, two feature vectors are pooled, in a hierarchical manner, over all sparse representation vectors of phase and contrast blocks by their corresponding dictionaries. Performance results of learning a regression model by the features acknowledge the superiority of the proposed method to state-of-the-art algorithms.

Despite the rapid growth of 3D displays in the last few years, insufficient supply of 3D contents has led to considerable effort in devising 2D to 3D conversion algorithms. Inferring associated depth from single 2D image is still a controversial issue in these algorithms. In this paper we propose an algorithm, which unlike previous strategies, aggregates both global and local information from a pool of images with known depth maps. Hence, we propose to extract a set of features from the image patches of globally similar images in a large 3D image repository. These features describe powerful monocular depth perception cues. Using these relevant and robust features and using modified stacked generalization learning scheme, our scheme directly extracts an accurate depth map from given images. Experimental results demonstrate that our method has surpassed state-of-the-art algorithms in both quantitative and qualitative analysis.

Sparse representations over redundant dictionaries have shown to produce high quality results in various signal and image processing tasks. Recent advancements in learning of the sparsifying dictionaries have made image compression based on sparse representation a promising field. In this paper, we present a boosted dictionary learning framework to construct an ensemble of complementary specialized dictionaries for sparse image representation. Boosted dictionaries along with a competitive sparse coding can provide us with more efficient sparse representations. Based on the proposed ensemble model, we then develop a new image compression algorithm using boosted multi-scale dictionaries learned in the wavelet domain. Our algorithm is evaluated for compression of natural images. Experimental results demonstrate that the proposed algorithm has better rate-distortion performance as compared with several competing compression methods including analytic and learned dictionary schemes.

Sparse representations over redundant learned dictionaries have shown to produce high quality results in various image processing tasks. An important characteristic of a learned dictionary is the mutual coherence of dictionary that affects its generalization performance and the optimality of sparse codes generated from it. In this paper, we present a dictionary learning model equipped with coherence regularization. For this model, two novel dictionary optimization algorithms based on group-wise minimization of inter- and intra-coherence penalties are proposed. Experimental results demonstrate that the proposed algorithms improve the generalization properties and sparse approximation performance of the trained dictionary compared to several incoherent dictionary learning methods.

Coronary artery disease is one of the major causes of death throughout the world. An effective method for diagnosing this disease is X-ray angiography. The images are usually of poor quality and low contrast. This is due to non-uniform illumination, appearance of other body organs and artifacts, low SNR values, etc. Accurate segmentation of arteries is a challenging and important task. In this paper we first extract coronary arteries region of interest (ROI) using Hessian filter. Then, we combine these results with the flux flow measurements for accurate identification of vessel pixels. Post processing is performed to eliminate falsely identified vessel pixels. Finally, we segment the coronary arteries by selecting the largest connected component. Qualitative and quantitative evaluations of our method show high effectiveness of the proposed method. In terms of capturing major vessels our method is successful in 96% of cases.

Melanoma is the deadliest form of skin cancer. Diagnosis of melanoma in early stages significantly enhances the survival rate. Recently there has been a rising trend in web-based and mobile applications for early detection of melanoma using images captured by conventional cameras. These images usually contain fewer detailed information in comparison with dermoscopic (microscopic) images. Meanwhile, non-dermoscopic images have the advantage of broad availability. In this paper a set of ten features is proposed which cover different color characteristics of melanoma visible in skin images. The first 5 features are extracted using Fuzzy C-means clustering based on color variations and color spatial distributions of pigmented skin. These features are shown to be discriminative for melanoma lesions. The next 5 features consider colors and intensity of the colors. Hence, a 10 dimensional color feature space is formed. Experimental results show that classification accuracy of suspicious moles, by the proposed set of features, outperforms comparable state-of-the-art methods.

With the increasing use of telemedicine there is a great demand in real-time processing and transmission of medical images. Noise is one of the important factors that degrade the quality of medical images. Impulse noise is a common noise that could be caused by malfunctioning of sensors or by data transmission errors. It is one the most common noises that have extensively been studied in recent years. For real-time noise removal hardware techniques are more suited, since software methods are complex and slow. Usually hardware techniques have low complexity and low accuracy. In this paper a low complexity, high accuracy, de-noising method is proposed. It first categorizes image pixels into a number of groups. Then noisy pixels are restored in different ways in each category. Local analysis of image blocks allows us to restore a noisy pixel by using its neighboring non-noisy pixels. All steps are designed to have low hardware complexity. Simulation results show that in the case of MR images, the proposed method removes impulse noise with acceptable accuracy.

Melanoma is the most aggressive form of skin cancer and is on rise. There exists a research trend for computerized analysis of suspicious skin lesions for malignancy using images captured by digital cameras. Analysis of these images is usually challenging due to existence of disturbing factors such as illumination variations and light reflections from skin surface. One important stage in diagnosis of melanoma is segmentation of lesion region from normal skin. In this paper, a method for accurate extraction of lesion region is proposed that is based on deep learning approaches. The input image, after being preprocessed to reduce noisy artifacts, is applied to a deep convolutional neural network (CNN). The CNN combines local and global contextual information and outputs a label for each pixel, producing a segmentation mask that shows the lesion region. This mask will be further refined by some post processing operations. The experimental results show that our proposed method can outperform the existing state-of-the-art algorithms in terms of segmentation accuracy.

Touchless communication is a new field for commanding electronic devices. This method is highlighted when hygiene is a special issue. Automated hand gesture recognition needs processing of hand images. Many research works have tried to cope with this recognition problem. Complexity and high computational costs are important drawbacks that make real-time execution of these algorithms difficult. In this paper a new hand gesture recognition method is proposed. To show the functionality of our method we show how it can be used for recognition of the number of fingers in segmented images. Also the proposed algorithm can estimate angles of fingers, direction of the hand, and positions of fingers. In this work, we transform an image to intercept-slope coordinate using a proposed Radon transform inspired mapping. Using this mapping, the algorithm becomes invariant to rotation, scale and position. Straight and separated fingers will be extracted and their locations and angles are feasible to be determined as well. Simplicity and robustness against rotation, scaling and position and also having no complex mathematical calculation are advantages of our work.

Inferring scene depth from a single monocular image is an essential component in several computer vision applications such as 3D modeling and robotics. This process is an ill-posed problem. To tackle this challenging problem, previous efforts have been focusing on exploiting only global or local depth aware properties. We propose a model that incorporates both of them to obtain significantly more accurate depth estimates than using either global or local properties alone. Specifically, we formulate single image depth estimation as a K nearest neighbor search problem at both image level and patch level. At each level, a set of rich depth aware features, describing monocular depth cues, is employed in a nearest-neighbor regression model. By comparing the results with and without patch based fusion, the importance of our joint local-global framework becomes clear. The experimental results also demonstrate superior performance compared with existing data-driven approaches in both quantitative and qualitative analyses with a significantly simpler algorithm than others.

Sparse representations over redundant dictionaries have shown to produce high-quality results in various signal and image processing tasks. Recent advancements in learning-based dictionary design have made image compression using data-adaptive learned dictionaries a promising field. In this paper, we present a boosted dictionary learning framework to construct an ensemble of complementary specialized dictionaries for sparse image representation. Boosted dictionaries along with a competitive sparse coding form our ensemble model which can provide us with more efficient sparse representations. The constituent dictionaries of the ensemble are obtained using a coherence regularized dictionary learning model for which two novel dictionary optimization algorithms are proposed. These algorithms improve the generalization properties of the trained dictionary compared with several incoherent dictionary learning methods. Based on the proposed ensemble model, we then develop a new image compression algorithm using boosted multi-scale dictionaries learned in the wavelet domain. Our algorithm is evaluated for the compression of natural images. Experimental results demonstrate that the proposed algorithm has better rate-distortion performance as compared with several competing compression methods, including analytic and learned dictionary schemes.

X-ray angiography is a standard method for diagnosing coronary artery diseases. In order to show coronary arteries, contrast agent and X-ray imaging are used but the produced images are not always of adequate quality for visual examination. The low quality is caused by different artifacts. The presence of catheter and also the surrounding tissues make the processing of these images more difficult. In this paper, we propose a fully automated method to enhance the angiogram images and detect the arteries. Our proposed method contains three main steps which are Hessian filter enhancement, feature extraction and vessel region detection. To further enhance the visual quality of the image, non-vessel areas are blurred. The enhanced images can be utilized for better diagnosis of coronary diseases such as stenosis. Subjective evaluation of the enhanced images shows the effectiveness and accuracy of the proposed method.

Segmentation of X-ray bone images is of concern in many medical applications such as detection of osteoporosis and bone fractures. Segmentation of such images is a challenging process. Varying brightness throughout the image makes it difficult to separate bones from background and soft tissue. Costume made as well as standard segmentation methods, such as active contour and region growing, have been applied to bone X-ray images. Although each method could perform well for some images, due to variety of bone structures and lighting conditions none of these methods can be considered as complete. In this paper we present a new bone segmentation method in which an image goes through preprocessing steps such as noise cancellation and edge detection. Analysis of intensity fluctuations in all rows of the image results in more accurate segmentation of bone regions. Visual evaluation show that the proposed algorithm segments bones better than conventional and some recent bone segmentation approaches.

Effective noise removal from image signals strongly relies on good image prior, which that comes from the ill-posed nature of image denoising problem. Nonlocal self-similarity and sparsity are two popular and widely used image priors which have led to several state-of-the-art methods in natural image denoising. In recent years, much progress has been made on low-rank modeling and it has achieved great successes in various image analysis problems. In this paper, we propose a new denoising algorithm based on iterative low-rank regularized collaborative filtering of image patches under a nonlocal framework. This collaborative filtering is formulated as recovery of low rank matrices from noisy data. Based on recent results from random matrix theory, an optimal singular value shrinkage operator is applied to efficiently solve this problem. Our experimental results demonstrate the superior denoising performance of the proposed algorithm as compared with the state-of-the-art methods.

The impedance plethysmography (IP) has long been used to monitor respiration. The IP signal is also suitable for portable monitoring of respiration due to its simplicity. However, this signal is very susceptible to motion artifact (MA). As a result, MA reduction is an indispensable part of portable acquisition of the IP signal. Often, the amplitude of the MA is much larger than the amplitude of the respiratory component in the IP signal. This study proposes a novel filtering method to remove the high-amplitude MA's from the IP signal. The proposed method combines the idea of ε-tube loss function and an autoregressive exogenous model to estimate the MA while leaving the periodic respiratory component of the IP signal intact. Also, a regularization method is used to find the best filter coefficients that maximize the regularity of the output signal. The results indicate that the proposed method can effectively remove the MA, outperforming the popular MA reduction methods. Several different performance measures are used for the comparison and the differences are found to be statistically significant.

This paper proposes a non-intrusive method to predict/estimate the intracranial pressure (ICP) level based on features extracted from multiple sources. Specifically, these features include midline shift measurement and texture features extracted from CT slices, as well as patient's demographic information, such as age. Injury Severity Score is also considered. After aggregating features from slices, a feature selection scheme is applied to select the most informative features. Support vector machine (SVM) is used to train the data and build the prediction model. The validation is performed with 10 fold cross validation. To avoid overfitting, all the feature selection and parameter selection are done using training data during the 10 fold cross validation for evaluation. This results an nested cross validation scheme implemented using Rapidminer. The final classification result shows the effectiveness of the proposed method in ICP prediction.

Fracture detection in cases of traumatic pelvic injuries is crucial for rapid and successful patient treatment. Initial diagnosis is typically made via X-ray images, which can be challenging and time-consuming to analyze due to their low resolution and the differing visual characteristics of fractures by their location. This paper presents a fracture detection method for the pelvic ring based on Discrete Wavelet Transform and boundary tracing applied to windows extracted from the ring, as defined by prior automated region segmentation via a deformable Spline/ASM model. Results so far are promising, and indicate that the approach can extract useful features for a trauma decision-making system to assist physicians and improve patient care.

Computer assisted medical image processing can extract vital information that may be elusive to human eyes. In this paper, an algorithm is proposed to automatically estimate the position of the actual midline from the brain CT scans using multiple regions shape matching. The method matches feature points identified from a set of ventricle templates, extracted from MRI, with the corresponding feature points in the segmented ventricles from CT images. Then based on the matched feature points, the position of the actual midline is estimated. The proposed multiple regions shape matching algorithm addresses the deformation problem arising from the intrinsic multiple regions nature of the brain ventricles. Experiments on the CT scans from patients with traumatic brain injuries (TBI) show promising results, particularly the proposed algorithm proves to be quite robust.

Error Correcting Output Codes (ECOC) method solves multiclass learning problems by combining the outputs of several binary classifiers according to an error correcting output code matrix. Traditionally, the minimum Hamming distance is adopted as the classification criterion to "vote" among multiple hypotheses, and the focus is given to the choice of error correcting output code matrix. In this paper, we apply a decoding methodology in multiclass learning problems, in which class labels of testing samples are unknown. In other words, without comparing the predicted and actual class labels, it can be known whether testing samples are classified correctly. Based on this property, a new cascade classifier is introduced. The classifier can improve the accuracy and will not result in over fitting. The analytical results show feasibility, accuracy, and the advantages of the proposed method.

In this paper, respiratory rate is extracted using signal processing and machine learning methods from electrical impedance, measured across arm. Two pairs of electrodes have been used along the arm, one for injecting the current, and one for sensing the voltage. After filtering, the frequency components and other signal features have been extracted using Short Time Fourier Transform (STFT). Then aSupport Vector Machine(SVM) model is trained to detect the breath-holding state. Frequency components and signal features of the parts of the signal that are detected to be representing the breathing state are then fed into another SVM model that extracts the respiratory rate and reduces the effect of motion artifacts. A similar method has been applied to the signal taken from end-tidal CO2respiratory measurement device as the reference signal. This signal has been used as the ground truth for training of the SVM model and for validation of the method. The results are validated using 5-fold cross-validation method. Statistical analysis confirms the significance of the introduced features.

Traumatic pelvic injuries are complex and difficult to treat, due to the high risk of complications. Prompt and accurate medical treatment is therefore vital. Computer-aided decision-making systems can assist physicians in this task, but none of those proposed so far incorporate features extracted from medical images. The study in this paper uses demographic information, standard medical measurements, and features extracted from X-ray images to predict a patient's length of stay in ICU via rules extracted from decision trees generated by the CART algorithm. The X-ray features are extracted by using a spline/ASM segmentation technique to detect structure position, then calculating measures of displacement. The results are promising and compare well with SVM and C4.5 algorithms, indicating that the rules represent true data patterns. Significantly, an X-ray feature is selected as highly important to injury severity, indicating that medical image features are important in providing accurate recommendations and predictions.

Traumatic pelvic injury is one of the life-threatening injuries because it is often associated with serious hemorrhage. Therefore, it is necessary to provide immediate medical treatments to the pelvic injury patients. But it is often difficult to make a decision because of a lot of similar cases existed. To help this problem, there are several medical applications designed to provide optimized management of hemorrhage during pelvic injuries. Even though they are useful, it is still necessary to have computer-aided system which assists either evaluating the severity of trauma or blood loss and making the most reliable medical treatments depending on the current status of patient by comparing the current trauma case with previously occurred cases, and helping trauma surgeons make more reliable and immediate decisions. Also it has been suggested that having a trauma system with the emphasis on optimal resource utilization and decision-making through computer aided decision-making systems offers the best chance to reduce the cost of trauma care [2]. In this paper, we designed an efficient computer assisted trauma decision making system for traumatic pelvic injuries. More specifically, a rule-based system is designed to create a reliable method of making predictions/recommendations on the status and outcome (ICU days) of treatments of pelvic trauma injuries using nonlinear regression methods and C4.5.

Biomedical image segmentation remains a challenging task mainly due to the weak edges and unevenly distributed color intensity of the objects and background. We present a novel unsupervised segmentation method to extract nuclei region from background. Our method, called shape stability algorithm, is a multiscale local adaptive threshold method. A modified weighted filter which serves as preprocessing method is also introduced. The presented algorithm is applied for segmentation of a number of Pap Smear images as well as bone marrow cell images. The results indicate the successful performance of the presented segmentation algorithm in segmentation of both Pap Smear and bone marrow samples.

The estimates of the posterior probabilities of the attributes in the image are widely used as criteria for image segmentation. The methods using this measure, however, suffer from intrinsic errors that occur around the boundary between regions. The errors are caused by estimating the posterior probabilities over the entire image. To resolve this problem, we define novel local posterior probabilities to better capture the local characteristics and then use them in an iterative segmentation process. Furthermore, the image itself is converted to another image in a new domain by a domain conversion method. It is shown that the converted image in the new domain is less susceptible to intrinsic errors.

BACKGROUND: The main goal in analyzing microarray data is to determine the genes that are differentially expressed across two types of tissue samples or samples obtained under two experimental conditions. Mixture model method (MMM hereafter) is a nonparametric statistical method often used for microarray processing applications, but is known to over-fit the data if the number of replicates is small. In addition, the results of the MMM may not be repeatable when dealing with a small number of replicates. In this paper, we propose a new version of MMM to ensure the repeatability of the results in different runs, and reduce the sensitivity of the results on the parameters. RESULTS: The proposed technique is applied to the two different data sets: Leukaemia data set and a data set that examines the effects of low phosphate diet on regular and Hyp mice. In each study, the proposed algorithm successfully selects genes closely related to the disease state that are verified by biological information. CONCLUSION: The results indicate 100% repeatability in all runs, and exhibit very little sensitivity on the choice of parameters. In addition, the evaluation of the applied method on the Leukaemia data set shows 12% improvement compared to the MMM in detecting the biologically-identified 50 expressed genes by Thomas et al. The results witness to the successful performance of the proposed algorithm in quantitative pathogenesis of diseases and comparative evaluation of treatment methods.

In this paper we present strategies to deal with inherent load uncertainties in future generation mobile networks. We address the interplay between user differentiation and resource allocation, and specifically the problem of CPU load control in a radio network controller (RNC).The algorithms we present distinguish between two types of uncertainty: the resource needs for arriving requests and the variation over time with respect to user service policies. We use feedback mechanisms inspired by automatic control techniques for the first type, and policy-dependent deterministic algorithms for the second type. We test alternative strategies in overload situations. One approach combines feedback control with a pool allocation mechanism, and a second is based on a rejection-ratio-minimising algorithm together with a state estimator.A simulation environment and traffic models for users with voice, mail, SMS and web browsing sessions were built for the purpose of evaluation of the above strategies. Our load control architectures were tested in comparison with an existing algorithm based on the leaky bucket principle. The studies show a superior behaviour with respect to load control in presence of relative user priorities, and minimal rejection criteria. Moreover, our architecture can be tuned to future developments with respect to user differentiation policy.

Recently, the complexity control of dynamic neural models has gained significant attention from signal processing community. The performance of such a process depends highly on the applied definition of "model complexity", i.e. complexity models that give simpler networks with better model accuracy and reliability are preferred. The learning theory creates a framework to assess the learning properties of models. These properties include the required size of the training samples as well as the statistical confidence over the model. In this paper, we apply the learning properties of two families of FIR radial basis function networks (RBFN's) to introduce new complexity measures that reflect the learning properties of such neural models. Then, based on these complexity terms, we define cost functions, which provide a balance between the training and testing performances of the model, and give desirable levels of accuracy and confidence.

For pt. I see ibid., vol.II, p.1321-4(2001). Recently, the complexity control of dynamic neural models has gained significant attention from the signal processing community. The performance of such a process depends highly on the applied definition of "model complexity", i.e. complexity models that give simpler networks with better model accuracy and reliability are preferred. The learning theory creates a framework to assess the learning properties of models. These properties include the required size of the training samples as well as the statistical confidence over the model. In this paper, we apply the learning properties of two families of FIR radial basis function networks (RBFN) to introduce new complexity measures that reflect the learning properties of such neural models. Then, based on these complexity terms, we define cost functions, which provide a balance between the training and testing performances of the model, and give desirable levels of accuracy and confidence.

Different methods of searching for dynamic neural models with minimum complexity have been proposed. The performance as well as the optimality of such methods highly depend on the way "model complexity" is defined. On the other hand, the learning theory creates a framework to assess the learning properties of models. These properties include the required size of the training samples as well as the statistical confidence over the model. In this paper, we first apply the learning properties of the reciprocal multi-quadratic radial basis function networks to introduce a new measure of complexity, which provides a balance between the training and testing performances of the model. Then, we present a systematic evolutionary programming technique that searches for a neural model of an unknown system with the optimal structure as well as parameters. The performance of the novel evolutionary method is illustrated by a numerical modeling simulation that testifies to the success of the proposed method.