AI Powers Breakthrough in Detecting Previously Invisible MS Brain Lesions

Researchers have developed a novel method utilizing artificial intelligence to detect brain lesions in multiple sclerosis (MS) patients that were previously undetectable with conventional MRI scans. This breakthrough could significantly advance the understanding and treatment of the debilitating neurological disease.

Multiple sclerosis occurs when the immune system attacks the nervous system, damaging the myelin sheath that protects nerve fibers. This damage disrupts communication signals between the brain and the body, leading to a wide range of symptoms such as fatigue, vision problems, muscle spasms, and cognitive difficulties. While MS affects approximately one million people in the U.S. and 150,000 in the UK, a significant portion of the disease's impact on brain gray matter has remained hidden.

Historically, MRI scans used to monitor MS patients could only identify lesions in the brain's white matter. Damage to the gray matter, responsible for processing information, movement, memory, and emotion, is known to be a major driver of disease progression, but visualizing these lesions has been a long-standing challenge for scientists. "Detecting previously invisible cortical lesions on conventional legacy MRI scans has major implications for MS research and clinical care," said Robert Zivadinov, a professor of neurology at the University at Buffalo and senior author on the study. "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."

The new technique employs AI to analyze and compare multiple types of MRI images of the same brain simultaneously. By identifying subtle differences invisible to the human eye, the AI can pinpoint lesions in the gray matter. In a study involving over 700 MS patients, this AI-driven approach identified more than 11,000 previously undetected gray matter lesions. The technology can also discern when brain tissue is not functioning normally.

"We have all been very frustrated, knowing that these cortical lesions were there but not being able to see them," said Michael G. Dwyer, the study's first author and associate professor of neurology and biomedical informatics at the Jacobs School. "There's a lot of ongoing damage that continues to happen in MS that you won't see with conventional MRI, but that histopathologists have been clearly demonstrating for decades on postmortem tissue." Dwyer added that the successful application of AI in this medical context is a significant achievement, providing access to previously unseen data within existing MRI scans.

MS lesions disrupt the brain's communication network by slowing or blocking nerve signals, contributing to many of the disease's debilitating symptoms. "This work, which has revealed that there is so much invisible pathology in the brain, will have tremendous impact for reviewing data from past clinical trials and also for those going forward," Professor Zivadinov noted.

MS typically first appears in individuals between 20 and 40 years old. While not usually fatal, advanced stages can lead to serious complications. There is currently no cure for MS, but available treatments aim to slow disease progression. The number of individuals living with MS has seen an increase in recent years, with the condition being more prevalent in women and people of European ancestry. The exact cause remains unclear, but genetic and environmental factors are believed to play a role.