Open AccessReview of advanced computational approaches on multiple sclerosis segmentation and classification
Author(s) -
Shanmuganathan Manimurugan,
Almutairi Saad,
Aborokbah Majed Mohammed,
Ganesan Subramaniam,
Ramachandran Varatharajan
Publication year - 2020
Publication title -
iet signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.384
H-Index - 42
eISSN - 1751-9683
pISSN - 1751-9675
DOI - 10.1049/iet-spr.2019.0543
Subject(s) - segmentation , computer science , categorization , artificial intelligence , pattern recognition (psychology) , process (computing) , principal component analysis , magnetic resonance imaging , image segmentation , machine learning , medicine , radiology , operating system
In this study, a survey of multiple sclerosis (MS) classification and segmentation process is presented, which is based on magnetic resonance imaging. Knowledge of MS lesions is gained by determining the number of sample lesions in order that the lesion development level can be followed precisely; therefore, the effects of pharmaceuticals in medical tests can be accurately assessed. Accurate recognition of MS lesions in magnetic resonance images is an additionally complex process because of their changing shapes and sizes which can be very difficult to identify based on anatomical positions in various subjects. This can be determined by precise segmentation; manual segmentation would be very difficult to perform as it requires high level knowledge which takes additional time. Inter‐ and intra‐expert variability need to be determined in order to perform the automated segmentation of lesions. The principal aim of this survey effort is to provide an analysis of the different categorization and segmentation methods and their techniques. This survey work will be valuable for researchers working in MS by considering and carefully evaluating the past work. The benefits and drawbacks of existing techniques are reviewed and the issue of MS lesion segmentation and classification is elucidated.