Research and development of automatic techniques for the detection, segmentation and analysis of multiple sclerosis plaques in magnetic resonance images

Abstract

Multiple Sclerosis (MS) is a complex multifactorial disease, demyelinating, autoimmune disease that affects the central nervous system and affects mainly young adults. It is considered an autoimmune disease because the immune system starts attacking the myelin sheath that covers neurons and compromises the function of the nervous system. The multimodal magnetic resonance imaging (MRI) has been very successfully used clinically for the diagnosis and monitoring of MS mainly due to the high resolution, good soft tissue differentiation, and for allowing the contrast of different information. The conventional method of measuring the volume of MS lesions is the manual delineation of lesions on MRI scans, performed by specialists with limited help from the computer. However, this procedure is arduous, time consuming, costly and is prone to large variability in inter-and intra-observer. Therefore, the main goal of this project is to develop computational techniques for automatic detection, measurement and analysis of the volume of MS plaques on MRI scans. (AU)