Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review

Abstract

In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre-processing, data-preparation and post-processing strategies available in these works. The aim of this study is three-fold. Our primary goal is to report how different CNN architectures have evolved, discuss state-of-the-art strategies, condense their results obtained using public datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in deep CNN for brain MRI analysis. Finally, we present a perspective on the future of CNNs in which we hint some of the research directions in subsequent years.

Contemporary Issues in Women's Health

“…Machine learning as the science of “artificial intelligence” (i.e., how computers learn from data), is rapidly evolving to include healthcare applications that could revolutionize medical imaging and diagnostics globally. Machine learning models for health are often based on convolutional neural networks (CNNs); the type of deep learning algorithms commonly applied to image classification and segmentation . Applications directly relevant to women's reproductive health include: reproductive medicine; obstetric imaging; breast imaging; and cervical cancer screening …”

“…Machine learning models for health are often based on convolutional neural networks (CNNs); the type of deep learning algorithms commonly applied to image classification and segmentation. [4][5][6] Applications directly relevant to women's reproductive health include: reproductive medicine 7 ; obstetric imaging 8,9 ; breast imaging 4,10 ; and cervical cancer screening. [11][12][13] In their recent study published in the Journal of the National Cancer Institute, Hu and colleagues assessed the performance of a machine learning model to evaluate cervical images for cancer screening.…”

End-to-end semantic segmentation of personalized deep brain structures for non-invasive brain stimulation

“…Convolutional neural networks are evolving as the state-of-art image segmentation techniques for brain MRI (Bernal et al, 2019). With deep learning network architectures, several automatic features can be observed by the network with no need of prior hand-crafted design .…”

Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network

“…After a review of these works in the literature, it has been observed that it is still challenging to determine which method performs the best classification to diagnose Alzheimer's disease from MR image data sets. CNNs are powerful for feature detection and extraction for brain image analysis . Therefore, in this work, we have motivated by the recent works and proposed a new fully automated robust 3D CNN architecture.…”

“…CNNs are powerful for feature detection and extraction for brain image analysis. 36 Therefore, in this work, we have motivated by the recent works and proposed a new fully automated robust 3D CNN architecture. In this architecture, three full-connected layers for differentiation of subjects and five convolutional layers for feature extraction have been used.…”