AUTHOR=Zeng Chenyi , Gu Lin , Liu Zhenzhong , Zhao Shen 

TITLE=Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2020.610967

DOI=10.3389/fninf.2020.610967

ISSN=1662-5196

ABSTRACT=In recent years, there have been multiple works of literature reviewing methods for automatically segmenting multiple sclerosis (MS) lesions. However, there is no literature to systematically and individually review deep learning-based MS lesion segmentation methods. This paper presents a systematic review of the literature in automated multiple sclerosis lesion segmentation based on deep learning. Manual segmentation of MS in magnetic resonance imaging is a challenging task due to intra-observer and inter-observer variability resulting in poor efficiency. To solve this problem, many automatic multiple sclerosis segmentation techniques have been proposed for the past few years. These methods can be classified into supervised and unsupervised learning according to whether label learning is used. Among these supervised learning methods, methods based on deep learning achieve pretty segmentation performance. In this paper, algorithms based on deep learning reviewed are divided into three different categories through their network structure feature, and their segmentation performance will also be analyzed and compared qualitatively and quantitatively. Finally, the future direction of the application of deep learning in MS lesion segmentation will be discussed.