In a new study published in Nature Communications, researchers tested MindGlide on over 14,000 images from more than 1,000 MS patients
UK researchers have developed a new artificial intelligence (AI) tool that can help interpret and assess how well treatments are working for patients with multiple sclerosis (MS).
MS is a condition where the immune system attacks the brain and spinal cord, causing problems in movement, sensation, and cognition.
The AI tool, called MindGlide, was developed by researchers at University College London (UCL). It uses mathematical models to train computers on massive amounts of data, solving complex problems like image recognition in human-like ways.
MindGlide can extract key information from brain MRI scans of MS patients, measuring damaged areas and highlighting subtle changes such as brain shrinkage and plaques. While MRI markers are crucial for studying MS, specialised scans are often required, limiting the utility of routine hospital MRIs.
“We hope that the tool will unlock valuable information from millions of untapped brain images that were previously difficult or impossible to understand, immediately leading to valuable insights into multiple sclerosis for researchers and, in the near future, to better understand a patient’s condition through AI in the clinic. We hope this will be possible in the next five to 10 years,” said Dr. Philipp Goebl from UCL’s Queen Square Institute of Neurology.
In a new study published in Nature Communications, researchers tested MindGlide on over 14,000 images from more than 1,000 MS patients.
MindGlide successfully detected how treatments affected disease progression in both clinical trials and routine care, using images that previously could not be analysed. The AI processed each image in just five to 10 seconds.
“Using MindGlide will enable us to use existing brain images in hospital archives to better understand multiple sclerosis and how treatment affects the brain,” Goebl added. The study found that MindGlide could accurately measure brain tissues and lesions even with limited MRI data, including T2-weighted MRI scans without FLAIR — a type of scan that highlights body fluids but makes plaques harder to see.
MindGlide also showed strong performance in detecting changes both on the brain’s surface and in deeper regions, with results consistent across single time points and longitudinal scans.
In addition, the AI tool was able to corroborate previous high-quality research on treatment efficacy.
