Title: Improved identification and quantification of lesions in multiple sclerosis

Authors: G. Wiselin Jiji

Addresses: Department of Computer Science & Engineering, Dr. Sivanthi Aditanar College of Engineering, Tiruchendur 628215, Chennai, India

Abstract: Correct identification of multiple sclerosis (MS) lesions in MRI is important for monitoring disease progression and for assessing treatment effects. We present a framework to automatically detect lesions of MS patients based on affine transformation followed by segmentation, background removal, and morphological filtering. The image processing procedure was tested with ten data sets of MRI images of several stages of multiple sclerosis. Analyses were also performed using the developed algorithm on the images obtained with different data sets. Compared to existing methods, this approach enhances the accuracy and reliability of proposed work.

Keywords: registration; image segmentation; lesion volume; lesion identification; lesion quantification; MS lesions; multiple sclerosis; MRI scans; magnetic resonance imaging; lesion detection; automatic detection; affine transformation; background removal; morphological filtering; image processing.

DOI: 10.1504/IJBET.2016.078339

International Journal of Biomedical Engineering and Technology, 2016 Vol.21 No.4, pp.361 - 378

Received: 19 Oct 2015
Accepted: 06 Dec 2015
Published online: 15 Aug 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article