TY - JOUR
T1 - Multiple sclerosis lesion analysis in brain magnetic resonance images
T2 - techniques and clinical applications
AU - Ma, Yang
AU - Zhang, Chaoyi
AU - Cabezas, Mariano
AU - Song, Yang
AU - Tang, Zihao
AU - Liu, Dongnan
AU - Cai, Weidong
AU - Barnett, Michael
AU - Wang, Chenyu
PY - 2022/6
Y1 - 2022/6
N2 - Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patient's neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors. Recently, automated statistical imaging analysis techniques have been proposed to detect and segment MS lesions based on MRI voxel intensity. However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions. By learning complex lesion representations directly from images, deep learning techniques have achieved remarkable breakthroughs in the MS lesion segmentation task. Here, we provide a comprehensive review of state-of-the-art automatic statistical and deep-learning MS segmentation methods and discuss current and future clinical applications. Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.
AB - Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patient's neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors. Recently, automated statistical imaging analysis techniques have been proposed to detect and segment MS lesions based on MRI voxel intensity. However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions. By learning complex lesion representations directly from images, deep learning techniques have achieved remarkable breakthroughs in the MS lesion segmentation task. Here, we provide a comprehensive review of state-of-the-art automatic statistical and deep-learning MS segmentation methods and discuss current and future clinical applications. Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.
KW - brain
KW - image segmentation
KW - lesion analysis
KW - magnetic resonance imaging
KW - multiple sclerosis
KW - review
UR - http://www.scopus.com/inward/record.url?scp=85124817436&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2022.3151741
DO - 10.1109/JBHI.2022.3151741
M3 - Article
C2 - 35171783
AN - SCOPUS:85124817436
SN - 2168-2194
VL - 26
SP - 2680
EP - 2692
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 6
ER -