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...

The functional connectivity (FC) patterns of resting-state functional magnetic resonance imaging (rs-fMRI) play an essential role in the development of autism spectrum disorders (ASD) classification models. There are available methods in literature that have used FC patterns as inputs for binary classification models, but the results barely reach an accuracy of 80%. Additionally, the generalizability across multiple sites of the models has not been investigated. Due to the lack of ASD subtypes identification model, the multi-class classification is proposed in the present study. This study aims to develop automated identification of autism spectrum disorder (ASD) subtypes using convolutional neural networks (CNN) using dynamic FC as its inputs. The rs-fMRI dataset used in this study consists of 144 individuals from 8 independent sites, labeled based on three ASD subtypes, namely autistic disorder (ASD), Asperger’s disorder (APD), and pervasive developmental disorder not otherwise specified (PDD-NOS). The blood-oxygen-level-dependent (BOLD) signals from 116 brain nodes of automated anatomical labeling (AAL) atlas are used, where the top-ranked node is determined based on one-way analysis of variance (ANOVA) of the power spectral density (PSD) values. Based on the statistical analysis of the PSD values of 3-level ASD and normal control (NC), putamen_R is obtained as the top-ranked node and used for the wavelet coherence computation. With good resolution in time and frequency domain, scalograms of wavelet coherence between the top-ranked node and the rest of the nodes are used as dynamic FC feature input to the convolutional neural networks (CNN). The dynamic FC patterns of wavelet coherence scalogram represent phase synchronization between the pairs of BOLD signals. Classification algorithms are developed using CNN and the wavelet coherence scalograms for binary and multi-class identification were trained and tested using cross-validation and leave-one-out techniques. Results of binary classification (ASD vs. NC) and multi-class classification (ASD vs. APD vs. PDD-NOS vs. NC) yielded, respectively, 89.8% accuracy and 82.1% macro-average accuracy, respectively. Findings from this study have illustrated the good potential of wavelet coherence technique in representing dynamic FC between brain nodes and open possibilities for its application in computer aided diagnosis of other neuropsychiatric disorders, such as depression or schizophrenia.

No abstract

Resting-state functional magnetic resonance imaging (rs-fMRI) is an efficient tool to measure brain connectivity and it can reveal patterns that distinguish autism spectrum disorder (ASD) from normal controls (NC). It is established that the fractal nature of neuroimaging signals will affect the estimation of brain's functional connectivity. Therefore, the ordinary correlation of rs-fMRI may not provide the original neuronal activity of the brain. In this work, the non-oscillatory brain connectivity method is proposed to distinguish subtypes of ASD from NC. The three subtypes of ASD namely autistic disorder (ATD), Asperger's disorder (APD), and Pervasive developmental disorder-not other specified (PDD) are classified from NC by extracting the non-oscillatory connectivity from the BOLD rs-fMRI signal. A number of significant connections are extracted by utilizing the p-value analysis and these significant connections are fed to machine learning (ML) classifiers for classification of ASD subtypes against normal control. The performance for binary classification is recorded at accuracy of 98.6%, 97.2%, 97.2%, respectively, for ATD vs. NC, APD vs. NC and PDD vs. NC. Whereas, for multiclass (ATD, APD, PDD and NC), the best accuracy is 88.9%. Both binary and multiclass classification outperformed the conventional Pearson correlation-based connectivity and benchmark approaches in terms of accuracy, sensitivity, specificity. This work demonstrates the great potential of non-oscillatory connectivity approaches, not only for autism diagnosis but also for other neurological disorders.

No abstract