DIAGNOSIS OF MULTIPLE SCLEROSIS DISEASE IN BRAIN MRI IMAGES USING MACHINE LEARNING AND DEEP LEARNING METHODS

Introduction: Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), whichcan lead to brain, spinal cord, and optic nerve problems. A total of ۲.۸ million are estimated tosuffer from MS. Globally, a new case of MS is reported every five minutes (۱).In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. Many machine learning and deep learning models have been developed using MRI images and clinical data with the aim of diagnosing and analyzing MS lesions (۲).Material and Methods: This study is a narrative review based on articles available in scientific databases such as PubMed, Scopus, Google Scholar, and our criteria for inclusion in the studies were the time and worthy quality of the publications, relevance and keywords.The keywords used included Magnetic resonance imaging, Machine learning, Deep learning and Multiple Sclerosis from ۲۰۱۸ to ۲۰۲۳.Results and Discussion: The results of various articles about machine vision methods for diagnosing MS lesions from MRI images were evaluated. In recent studies, researchers have focused on the applications of machine vision techniques in MS disease, including diagnosing plaque type, predicting treatment response, segmenting MS lesions, and classifying patients (۲, ۳).Conclusion: MS is a chronic disease that directly attacks the central nervous system. Early diagnosis of MS is of great significance as it can prevent the progression of the disease. The aim of new studies shows that the use of artificial intelligence solutions and utilizing machine learning and deep learning algorithms in the medical field has improved the diagnosis and prognosis of MS patients.

Keywords:

“Multiple Sclerosis” , “Machine learning” , “Deep Learning” , ”Magnetic Resonance Imaging