Kidney Segmentation from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Integrating Deep Convolutional Neural Networks and Level Set Methods.

The dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique has taken on a significant and increasing role in diagnostic procedures and treatments for patients who suffer from chronic kidney disease. Careful segmentation of kidneys from DCE-MRI scans is an essential early step towards the evaluation of kidney function. Recently, deep convolutional neural networks have increased in popularity in medical image segmentation. To this end, in this paper, we propose a new and fully automated two-phase approach that integrates convolutional neural networks and level set methods to delimit kidneys in DCE-MRI scans. We first develop two convolutional neural networks that rely on the U-Net structure (UNT) to predict a kidney probability map for DCE-MRI scans. Then, to leverage the segmentation performance, the pixel-wise kidney probability map predicted from the deep model is exploited with the shape prior information in a level set method to guide the contour evolution towards the target kidney. Real DCE-MRI datasets of 45 subjects are used for training, validating, and testing the proposed approach. The valuation results demonstrate the high performance of the two-phase approach, achieving a Dice similarity coefficient of 0.95 ± 0.02 and intersection over union of 0.91 ± 0.03, and 1.54 ± 1.6 considering a 95% Hausdorff distance. Our intensive experiments confirm the potential and effectiveness of that approach over both UNT models and numerous recent level set-based methods.

Level-Set-Based Kidney Segmentation from DCE-MRI Using Fuzzy Clustering with Population-Based and Subject-Specific Shape Statistics.

The segmentation of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) of the kidney is a fundamental step in the early and noninvasive detection of acute renal allograft rejection. In this paper, a new and accurate DCE­MRI kidney segmentation method is proposed. In this method, fuzzy c-means (FCM) clustering is embedded into a level set method, with the fuzzy memberships being iteratively updated during the level set contour evolution. Moreover, population­based shape (PB-shape) and subject-specific shape (SS-shape) statistics are both exploited. The PB-shape model is trained offline from ground-truth kidney segmentations of various subjects, whereas the SS-shape model is trained on the fly using the segmentation results that are obtained for a specific subject. The proposed method was evaluated on the real medical datasets of 45 subjects and reports a Dice similarity coefficient (DSC) of 0.953 ± 0.018, an intersection-over-union (IoU) of 0.91 ± 0.033, and 1.10 ± 1.4 in the 95-percentile of Hausdorff distance (HD95). Extensive experiments confirm the superiority of the proposed method over several state-of-the-art level set methods, with an average improvement of 0.7 in terms of HD95. It also offers an HD95 improvement of 9.5 and 3.8 over two deep neural networks based on the U-Net architecture. The accuracy improvements have been experimentally found to be more prominent on low-contrast and noisy images.

Kidney segmentation from DCE-MRI converging level set methods, fuzzy clustering and Markov random field modeling.

Early diagnosis of transplanted kidney function requires precise Kidney segmentation from Dynamic Contrast-Enhanced Magnetic Resonance Imaging images as a preliminary step. In this regard, this paper aims to propose an automated and accurate DCE-MRI kidney segmentation method integrating fuzzy c-means (FCM) clustering and Markov random field modeling into a level set formulation. The fuzzy memberships, kidney's shape prior model, and spatial interactions modeled using a second-order MRF guide the LS contour evolution towards the target kidney. Several experiments on real medical data of 45 subjects have shown that the proposed method can achieve high and consistent segmentation accuracy regardless of where the LS contour was initialized. It achieves an accuracy of 0.956 ± 0.019 in Dice similarity coefficient (DSC) and 1.15 ± 1.46 in 95% percentile of Hausdorff distance (HD95). Our quantitative comparisons confirm the superiority of the proposed method over several LS methods with an average improvement of more than 0.63 in terms of HD95. It also offers HD95 improvements of 9.62 and 3.94 over two deep neural networks based on the U-Net model. The accuracy improvements are experimentally found to be more profound on low-contrast images as well as DCE-MRI images with high noise levels.

A New Framework for Precise Identification of Prostatic Adenocarcinoma.

Prostate cancer, which is also known as prostatic adenocarcinoma, is an unconstrained growth of epithelial cells in the prostate and has become one of the leading causes of cancer-related death worldwide. The survival of patients with prostate cancer relies on detection at an early, treatable stage. In this paper, we introduce a new comprehensive framework to precisely differentiate between malignant and benign prostate cancer. This framework proposes a noninvasive computer-aided diagnosis system that integrates two imaging modalities of MR (diffusion-weighted (DW) and T2-weighted (T2W)). For the first time, it utilizes the combination of functional features represented by apparent diffusion coefficient (ADC) maps estimated from DW-MRI for the whole prostate in combination with texture features with its first- and second-order representations, extracted from T2W-MRIs of the whole prostate, and shape features represented by spherical harmonics constructed for the lesion inside the prostate and integrated with PSA screening results. The dataset presented in the paper includes 80 biopsy confirmed patients, with a mean age of 65.7 years (43 benign prostatic hyperplasia, 37 prostatic carcinomas). Experiments were conducted using different well-known machine learning approaches including support vector machines (SVM), random forests (RF), decision trees (DT), and linear discriminant analysis (LDA) classification models to study the impact of different feature sets that lead to better identification of prostatic adenocarcinoma. Using a leave-one-out cross-validation approach, the diagnostic results obtained using the SVM classification model along with the combined feature set after applying feature selection (88.75% accuracy, 81.08% sensitivity, 95.35% specificity, and 0.8821 AUC) indicated that the system's performance, after integrating and reducing different types of feature sets, obtained an enhanced diagnostic performance compared with each individual feature set and other machine learning classifiers. In addition, the developed diagnostic system provided consistent diagnostic performance using 10-fold and 5-fold cross-validation approaches, which confirms the reliability, generalization ability, and robustness of the developed system.

The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients.

Early grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from Computed Tomography (CT) images. This system segments the lung region from chest CT scans using an unsupervised approach based on an appearance model, followed by 3D rotation invariant Markov-Gibbs Random Field (MGRF)-based morphological constraints. This system analyzes the segmented lung and generates precise, analytical imaging markers by estimating the MGRF-based analytical potentials. Three Gibbs energy markers were extracted from each CT scan by tuning the MGRF parameters on each lesion separately. The latter were healthy/mild, moderate, and severe lesions. To represent these markers more reliably, a Cumulative Distribution Function (CDF) was generated, then statistical markers were extracted from it, namely, 10th through 90th CDF percentiles with 10% increments. Subsequently, the three extracted markers were combined together and fed into a backpropagation neural network to make the diagnosis. The developed system was assessed on 76 COVID-19-infected patients using two metrics, namely, accuracy and Kappa. In this paper, the proposed system was trained and tested by three approaches. In the first approach, the MGRF model was trained and tested on the lungs. This approach achieved 95.83% accuracy and 93.39% kappa. In the second approach, we trained the MGRF model on the lesions and tested it on the lungs. This approach achieved 91.67% accuracy and 86.67% kappa. Finally, we trained and tested the MGRF model on lesions. It achieved 100% accuracy and 100% kappa. The results reported in this paper show the ability of the developed system to accurately grade COVID-19 lesions compared to other machine learning classifiers, such as k-Nearest Neighbor (KNN), decision tree, naïve Bayes, and random forest.

COVID-19 and myocarditis: a brief review.

Cardiovascular complications (especially myocarditis) related to COVID-19 viral infection are not well understood, nor do they possess a well recognized diagnostic protocol as most of our information regarding this issue was derived from case reports. In this article we extract data from all published case reports in the second half of 2020 to summarize the theories of pathogenesis and explore the value of each diagnostic test including clinical, lab, ECG, ECHO, cardiac MRI and endomyocardial biopsy. These tests provide information that explain the mechanism of development of myocarditis that further paves the way for better management.

Variational Approach for Joint Kidney Segmentation and Registration from DCE-MRI Using Fuzzy Clustering with Shape Priors.

The dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique has great potential in the diagnosis, therapy, and follow-up of patients with chronic kidney disease (CKD). Towards that end, precise kidney segmentation from DCE-MRI data becomes a prerequisite processing step. Exploiting the useful information about the kidney's shape in this step mandates a registration operation beforehand to relate the shape model coordinates to those of the image to be segmented. Imprecise alignment of the shape model induces errors in the segmentation results. In this paper, we propose a new variational formulation to jointly segment and register DCE-MRI kidney images based on fuzzy c-means clustering embedded within a level-set (LSet) method. The image pixels' fuzzy memberships and the spatial registration parameters are simultaneously updated in each evolution step to direct the LSet contour toward the target kidney. Results on real medical datasets of 45 subjects demonstrate the superior performance of the proposed approach, reporting a Dice similarity coefficient of 0.94 ± 0.03, Intersection-over-Union of 0.89 ± 0.05, and 2.2 ± 2.3 in 95-percentile of Hausdorff distance. Extensive experiments show that our approach outperforms several state-of-the-art LSet-based methods as well as two UNet-based deep neural models trained for the same task in terms of accuracy and consistency.

A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens.

Prostate cancer is a significant cause of morbidity and mortality in the USA. In this paper, we develop a computer-aided diagnostic (CAD) system for automated grade groups (GG) classification using digitized prostate biopsy specimens (PBSs). Our CAD system aims to firstly classify the Gleason pattern (GP), and then identifies the Gleason score (GS) and GG. The GP classification pipeline is based on a pyramidal deep learning system that utilizes three convolution neural networks (CNN) to produce both patch- and pixel-wise classifications. The analysis starts with sequential preprocessing steps that include a histogram equalization step to adjust intensity values, followed by a PBSs' edge enhancement. The digitized PBSs are then divided into overlapping patches with the three sizes: 100 × 100 (CNNS), 150 × 150 (CNNM), and 200 × 200 (CNNL), pixels, and 75% overlap. Those three sizes of patches represent the three pyramidal levels. This pyramidal technique allows us to extract rich information, such as that the larger patches give more global information, while the small patches provide local details. After that, the patch-wise technique assigns each overlapped patch a label as GP categories (1 to 5). Then, the majority voting is the core approach for getting the pixel-wise classification that is used to get a single label for each overlapped pixel. The results after applying those techniques are three images of the same size as the original, and each pixel has a single label. We utilized the majority voting technique again on those three images to obtain only one. The proposed framework is trained, validated, and tested on 608 whole slide images (WSIs) of the digitized PBSs. The overall diagnostic accuracy is evaluated using several metrics: precision, recall, F1-score, accuracy, macro-averaged, and weighted-averaged. The (CNNL) has the best accuracy results for patch classification among the three CNNs, and its classification accuracy is 0.76. The macro-averaged and weighted-average metrics are found to be around 0.70-0.77. For GG, our CAD results are about 80% for precision, and between 60% to 80% for recall and F1-score, respectively. Also, it is around 94% for accuracy and NPV. To highlight our CAD systems' results, we used the standard ResNet50 and VGG-16 to compare our CNN's patch-wise classification results. As well, we compared the GG's results with that of the previous work.

Early assessment of lung function in coronavirus patients using invariant markers from chest X-rays images.

The primary goal of this manuscript is to develop a computer assisted diagnostic (CAD) system to assess pulmonary function and risk of mortality in patients with coronavirus disease 2019 (COVID-19). The CAD system processes chest X-ray data and provides accurate, objective imaging markers to assist in the determination of patients with a higher risk of death and thus are more likely to require mechanical ventilation and/or more intensive clinical care.To obtain an accurate stochastic model that has the ability to detect the severity of lung infection, we develop a second-order Markov-Gibbs random field (MGRF) invariant under rigid transformation (translation or rotation of the image) as well as scale (i.e., pixel size). The parameters of the MGRF model are learned automatically, given a training set of X-ray images with affected lung regions labeled. An X-ray input to the system undergoes pre-processing to correct for non-uniformity of illumination and to delimit the boundary of the lung, using either a fully-automated segmentation routine or manual delineation provided by the radiologist, prior to the diagnosis. The steps of the proposed methodology are: (i) estimate the Gibbs energy at several different radii to describe the inhomogeneity in lung infection; (ii) compute the cumulative distribution function (CDF) as a new representation to describe the local inhomogeneity in the infected region of lung; and (iii) input the CDFs to a new neural network-based fusion system to determine whether the severity of lung infection is low or high. This approach is tested on 200 clinical X-rays from 200 COVID-19 positive patients, 100 of whom died and 100 who recovered using multiple training/testing processes including leave-one-subject-out (LOSO), tenfold, fourfold, and twofold cross-validation tests. The Gibbs energy for lung pathology was estimated at three concentric rings of increasing radii. The accuracy and Dice similarity coefficient (DSC) of the system steadily improved as the radius increased. The overall CAD system combined the estimated Gibbs energy information from all radii and achieved a sensitivity, specificity, accuracy, and DSC of 100%, 97% ± 3%, 98% ± 2%, and 98% ± 2%, respectively, by twofold cross validation. Alternative classification algorithms, including support vector machine, random forest, naive Bayes classifier, K-nearest neighbors, and decision trees all produced inferior results compared to the proposed neural network used in this CAD system. The experiments demonstrate the feasibility of the proposed system as a novel tool to objectively assess disease severity and predict mortality in COVID-19 patients. The proposed tool can assist physicians to determine which patients might require more intensive clinical care, such a mechanical respiratory support.

Precise Identification of Prostate Cancer from DWI Using Transfer Learning.

Background and Objective: The use of computer-aided detection (CAD) systems can help radiologists make objective decisions and reduce the dependence on invasive techniques. In this study, a CAD system that detects and identifies prostate cancer from diffusion-weighted imaging (DWI) is developed. Methods: The proposed system first uses non-negative matrix factorization (NMF) to integrate three different types of features for the accurate segmentation of prostate regions. Then, discriminatory features in the form of apparent diffusion coefficient (ADC) volumes are estimated from the segmented regions. The ADC maps that constitute these volumes are labeled by a radiologist to identify the ADC maps with malignant or benign tumors. Finally, transfer learning is used to fine-tune two different previously-trained convolutional neural network (CNN) models (AlexNet and VGGNet) for detecting and identifying prostate cancer. Results: Multiple experiments were conducted to evaluate the accuracy of different CNN models using DWI datasets acquired at nine distinct b-values that included both high and low b-values. The average accuracy of AlexNet at the nine b-values was 89.2±1.5% with average sensitivity and specificity of 87.5±2.3% and 90.9±1.9%. These results improved with the use of the deeper CNN model (VGGNet). The average accuracy of VGGNet was 91.2±1.3% with sensitivity and specificity of 91.7±1.7% and 90.1±2.8%. Conclusions: The results of the conducted experiments emphasize the feasibility and accuracy of the developed system and the improvement of this accuracy using the deeper CNN.

Role of AI and Histopathological Images in Detecting Prostate Cancer: A Survey.

Prostate cancer is one of the most identified cancers and second most prevalent among cancer-related deaths of men worldwide. Early diagnosis and treatment are substantial to stop or handle the increase and spread of cancer cells in the body. Histopathological image diagnosis is a gold standard for detecting prostate cancer as it has different visual characteristics but interpreting those type of images needs a high level of expertise and takes too much time. One of the ways to accelerate such an analysis is by employing artificial intelligence (AI) through the use of computer-aided diagnosis (CAD) systems. The recent developments in artificial intelligence along with its sub-fields of conventional machine learning and deep learning provide new insights to clinicians and researchers, and an abundance of research is presented specifically for histopathology images tailored for prostate cancer. However, there is a lack of comprehensive surveys that focus on prostate cancer using histopathology images. In this paper, we provide a very comprehensive review of most, if not all, studies that handled the prostate cancer diagnosis using histopathological images. The survey begins with an overview of histopathological image preparation and its challenges. We also briefly review the computing techniques that are commonly applied in image processing, segmentation, feature selection, and classification that can help in detecting prostate malignancies in histopathological images.

3D kidney segmentation from abdominal diffusion MRI using an appearance-guided deformable boundary.

A new technique for more accurate automatic segmentation of the kidney from its surrounding abdominal structures in diffusion-weighted magnetic resonance imaging (DW-MRI) is presented. This approach combines a new 3D probabilistic shape model of the kidney with a first-order appearance model and fourth-order spatial model of the diffusion-weighted signal intensity to guide the evolution of a 3D geometric deformable model. The probabilistic shape model was built from labeled training datasets to produce a spatially variant, independent random field of region labels. A Markov-Gibbs random field spatial model with up to fourth-order interactions was adequate to capture the inhomogeneity of renal tissues in the DW-MRI signal. A new analytical approach estimated the Gibbs potentials directly from the DW-MRI data to be segmented, in order that the segmentation procedure would be fully automatic. Finally, to better distinguish the kidney object from the surrounding tissues, marginal gray level distributions inside and outside of the deformable boundary were modeled with adaptive linear combinations of discrete Gaussians (first-order appearance model). The approach was tested on a cohort of 64 DW-MRI datasets with b-values ranging from 50 to 1000 s/mm2. The performance of the presented approach was evaluated using leave-one-subject-out cross validation and compared against three other well-known segmentation methods applied to the same DW-MRI data using the following evaluation metrics: 1) the Dice similarity coefficient (DSC); 2) the 95-percentile modified Hausdorff distance (MHD); and 3) the percentage kidney volume difference (PKVD). High performance of the new approach was confirmed by the high DSC (0.95±0.01), low MHD (3.9±0.76) mm, and low PKVD (9.5±2.2)% relative to manual segmentation by an MR expert (a board certified radiologist).

A New Local Fractional Entropy-Based Model for Kidney MRI Image Enhancement.

Kidney image enhancement is challenging due to the unpredictable quality of MRI images, as well as the nature of kidney diseases. The focus of this work is on kidney images enhancement by proposing a new Local Fractional Entropy (LFE)-based model. The proposed model estimates the probability of pixels that represent edges based on the entropy of the neighboring pixels, which results in local fractional entropy. When there is a small change in the intensity values (indicating the presence of edge in the image), the local fractional entropy gives fine image details. Similarly, when no change in intensity values is present (indicating smooth texture), the LFE does not provide fine details, based on the fact that there is no edge information. Tests were conducted on a large dataset of different, poor-quality kidney images to show that the proposed model is useful and effective. A comparative study with the classical methods, coupled with the latest enhancement methods, shows that the proposed model outperforms the existing methods.

Model-wise and point-wise random sample consensus for robust regression and outlier detection.

Popular regression techniques often suffer at the presence of data outliers. Most previous efforts to solve this problem have focused on using an estimation algorithm that minimizes a robust M-estimator based error criterion instead of the usual non-robust mean squared error. However the robustness gained from M-estimators is still low. This paper addresses robust regression and outlier detection in a random sample consensus (RANSAC) framework. It studies the classical RANSAC framework and highlights its model-wise nature for processing the data. Furthermore, it introduces for the first time a point-wise strategy of RANSAC. New estimation algorithms are developed following both the model-wise and point-wise RANSAC concepts. The proposed algorithms' theoretical robustness and breakdown points are investigated in a novel probabilistic setting. While the proposed concepts and algorithms are generic and general enough to adopt many regression machineries, the paper focuses on multilayered feed-forward neural networks in solving regression problems. The algorithms are evaluated on synthetic and real data, contaminated with high degrees of outliers, and compared to existing neural network training algorithms. Furthermore, to improve the time performance, parallel implementations of the two algorithms are developed and assessed to utilize the multiple CPU cores available on nowadays computers.

Development of a micro-gripper using piezoelectric bimorphs.

Piezoelectric bimorphs have been used as a micro-gripper in many applications, but the system might be complex and the response performance might not have been fully characterized. In this study the dynamic characteristics of bending piezoelectric bimorphs actuators were theoretically and experimentally investigated for micro-gripping applications in terms of deflection along the length, transient response, and frequency response with varying driving voltages and driving signals. In addition, the implementation of a parallel micro-gripper using bending piezoelectric bimorphs was presented. Both fingers were actuated separately to perform mini object handling. The bending piezoelectric bimorphs were fixed as cantilevers and individually driven using a high voltage amplifier and the bimorph deflection was measured using a non contact proximity sensor attached at the tip of one finger. The micro-gripper could perform precise micro-manipulation tasks and could handle objects down to 50 µm in size. This eliminates the need for external actuator extension of the microgripper as the grasping action was achieved directly with the piezoelectric bimorph, thus minimizing the weight and the complexity of the micro-gripper.

Random sampler M-estimator algorithm with sequential probability ratio test for robust function approximation via feed-forward neural networks.

This paper addresses the problem of fitting a functional model to data corrupted with outliers using a multilayered feed-forward neural network. Although it is of high importance in practical applications, this problem has not received careful attention from the neural network research community. One recent approach to solving this problem is to use a neural network training algorithm based on the random sample consensus (RANSAC) framework. This paper proposes a new algorithm that offers two enhancements over the original RANSAC algorithm. The first one improves the algorithm accuracy and robustness by employing an M-estimator cost function to decide on the best estimated model from the randomly selected samples. The other one improves the time performance of the algorithm by utilizing a statistical pretest based on Wald's sequential probability ratio test. The proposed algorithm is successfully evaluated on synthetic and real data, contaminated with varying degrees of outliers, and compared with existing neural network training algorithms.