Researchers have developed a novel approach utilizing artificial intelligence (AI) to detect brain lesions in multiple sclerosis (MS) patients that were previously invisible on conventional MRI scans. This development could significantly advance the understanding and treatment of MS, a chronic disease affecting the nervous system.
Multiple sclerosis occurs when the immune system mistakenly attacks the body's own nervous system, specifically targeting the myelin sheath, the protective coating around nerve fibers. This damage disrupts communication signals between the brain and the rest of the body, leading to a wide range of symptoms such as fatigue, vision problems, muscle spasms, memory difficulties, and balance issues. While MS affects around 150,000 people in the UK and nearly three million worldwide, including approximately one million in the US, there is currently no cure.
Historically, MRI scans used in MS monitoring could only detect lesions in the brain's white matter. However, damage to the grey matter, which is crucial for processing information, movement, memory, and emotion, is known to be a major driver of disease progression. Until now, the inability to visualize these grey matter lesions has limited researchers' ability to track this hidden damage and develop targeted treatments.
The new technique, developed by scientists at the University at Buffalo, employs AI to analyze and compare multiple types of MRI images of the same brain simultaneously. By examining scans from over 700 MS patients, the AI identified more than 11,000 previously undetectable grey matter lesions. The system can detect subtle differences between images that are imperceptible to the human eye, and can also identify tissue that is not functioning like healthy brain tissue.
"The ability to see for the first time these previously hidden indicators of MS disease progression, including cognitive impairment and disability, is an important advance," said Robert Zivadinov, a professor of neurology at the University of Buffalo and senior author of the study. Michael G. Dwyer, the study's first author and associate professor of neurology and biomedical informatics, added that the AI's capability to reveal these lesions is a significant success for applying AI in medicine, providing access to crucial data that was previously inaccessible.
Lesions in the brain and spinal cord are characteristic of MS and are believed to cause many of the disease's debilitating symptoms by slowing or blocking nerve signals. The researchers believe this new method will have a substantial impact on the review of data from past clinical trials and inform future research. The number of individuals living with MS has been increasing, with an estimated 20,000 more people diagnosed in Britain since 2019. Symptoms typically first appear between the ages of 20 and 40, and the condition is more prevalent in women and individuals of European ancestry.