Supervised and Unsupervised Machine Learning Techniques for Multiple Sclerosis Identification: A Performance Comparative Analysis

Abstract

The identification of multiple sclerosis disease (MSD) is very crucial because it is a neurological disease in young people where an early detection is recommended. Accurate classification and segmentation using distinct machine learning techniques plays significant role in identifying MSD based on brain magnetic resonance (MR) images. In this work, a performance comparative analysis of various supervised and unsupervised machine learning techniques on eighteen gray level textural feature matrix (GLTFM) of brain MR images has been performed. Supervised machine learning (k-nearest neighbor, support vector machine and ensemble learning) classification techniques are utilized for MSD identification and compared with unsupervised machine learning-based clustering techniques (k-mean clustering and Gaussian mixture model). Accuracy has been evaluated for measuring proposed system’s execution on unhealthy brain magnetic resonance (MR) images from the e-health dataset and healthy control brain magnetic resonance (MR) images from private clinical dataset. These metrics are also compared with various state-of-the-art techniques. It has been verified that MSD identification from healthy and unhealthy brain MR images based on the proposed methodology using supervised machine learning techniques yields accuracy of 96.55% which is better than existing state-of-the-art techniques and unsupervised machine learning techniques.