In this paper, we present an evaluation of four encoder–decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder–decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92.8 % . This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.

BackgroundSpectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology of the retina as well as the retina layers.MethodsThe dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px × 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations.Results and conclusionBesides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5%, respectively.

World-wide incidence rate of prostate cancer has progressively increased with time especially with the increased proportion of elderly population. Early detection of prostate cancer when it is confined to the prostate gland has the best chance of successful treatment and increase in surviving rate. Prostate cancer occurrence rate varies over the three prostate regions, peripheral zone (PZ), transitional zone (TZ), and central zone (CZ) and this characteristic is one of the important considerations is development of segmentation algorithm. In fact, the occurrence rate of cancer PZ, TZ and CZ regions is respectively. at 70-80%, 10-20%, 5% or less. In general application of medical imaging, segmentation tasks can be time consuming for the expert to delineate the region of interest, especially when involving large numbers of images. In addition, the manual segmentation is subjective depending on the expert's experience. Hence, the need to develop automatic segmentation algorithms has rapidly increased along with the increased need of diagnostic tools for assisting medical practitioners, especially in the absence of radiologists. The prostate gland segmentation is challenging due to its shape variability in each zone from patient to patient and different tumor levels in each zone. This survey reviewed 22 machine learning and 88 deep learningbased segmentation of prostate MRI papers, including all MRI modalities. The review coverage includes the initial screening and imaging techniques, image pre-processing, segmentation techniques based on machine learning and deep learning techniques. Particular attention is given to different loss functions used for training segmentation based on deep learning techniques. Besides, a summary of publicly available prostate MRI image datasets is also provided. Finally, the future challenges and limitations of current deep learningbased approaches and suggestions of potential future research are also discussed. INDEX TERMS MRI, prostate cancer, deep learning, automatic algorithms, prostate gland I. INTRODUCTIONP ROSTATE cancer is a significant global public health issue and has ranked as the second world's prevalent cancers in male after lung cancer. Diagnosis of prostate cancer has become a challenging task with a progression rate of 1 in 6 men affected throughout their lives, and 1 in 36 died from the disease, being the second most common cause of death among men [1], [2]. According to the study in [3], prostate cancer ratio is the highest in the United States (USA) at 21% whereas it ranges from 1 to 9 in 100,00 men in Northern Europe, North America, New Zealand, and Australia. In 2019, among the various types of cancer, including breast cancer, lung cancer, colon, and rectum cancer, prostate 13 cancer has recorded 174,650 new prostate cancer cases, and 14 31,620 cancer deaths in the U.S. [4]. The survival rate of 15 individuals affected with prostate cancer is relatively high. 16 However, human aging factors would exacerbate the disease 17 and spread cancer to other organs if left un...

Neuroimaging investigations have proven that social anxiety disorder (SAD) is associated with aberrations in the connectivity of human brain functions.The assessment of the effective connectivity (EC) of the brain and its impact on the detection and medication of neurodegenerative pathophysiology is hence a crucial concern that needs to be addressed. Nevertheless, there are no clinically certain diagnostic biomarkers that can be linked to SAD. Therefore, investigating neural connectivity biomarkers of SAD based on deep learning models (DL) has a promising approach with its recent underlined potential results. In this study, an electroencephalography (EEG)-based detection model for SAD is constructed through directed causal influences combined with a deep convolutional neural network (CNN) and the long shortterm memory (LSTM). The EEG data were classified by applying three different DL models, namely, CNN, LSTM, and CNN+LSTM to discriminate the severity of SAD (severe, moderate, mild) and healthy controls (HC) at different frequency bands (delta, theta, alpha, low beta, and high beta) in the default mode network (DMN) under resting-state condition. The DL model uses the EC features as input, which are derived from the cortical correlation within different EEG rhythms for certain cortical areas that are more susceptible to SAD. Experimental results revealed that the proposed model (CNN+LSTM) outperforms the other models in SAD recognition. For our dataset, the highest recognition accuracies of 92.86%, 92.86%, 96.43%, and 89.29%, specificities of 95.24%, 95.24%, 100%, and 90.91%, and sensitivities of 85.71%, 85.71%, 87.50%, and 83.33% were achieved by using CNN+LSTM model for severe, moderate, mild, and HC, respectively. The fundamental contribution of this analysis is the characterization of neural brain features using different DL models to categorize the severity of SAD, which can represent a potential biomarker for SAD.INDEX TERMS Effective connectivity network, convolutional neural networks (CNNs), social anxiety disorder (SAD), default mode network (DMN), deep learning models, partial directed coherence (PDC), Electroencephalogram (EEG), human brain mapping.