AI reveals MS cortical lesions
Analysis based on 7 articles · First reported Jul 07, 2026 · Last updated Jul 10, 2026
The breakthrough could enhance MS drug development by enabling better assessment of treatment effects on cortical lesions, potentially benefiting companies like F. Hoffmann-La Roche — Genentech. However, clinical adoption is years away, so near-term market impact is limited.
A University at Buffalo-led team published a paper in Tata Communications on July 7, 2026, demonstrating that AI-enhanced image processing can detect cortical lesions in multiple sclerosis (MS) patients from conventional MRI scans. Cortical lesions in the brain's gray matter are strongly linked to MS progression and cognitive impairment but have been largely invisible on standard MRI. The researchers applied techniques including a new method called multimodal cortical lesion enhancement (MMCLE) to MRI data from the phase III ORATORIO trial of Ocrelizumab, detecting over 10,000 cortical lesions across 732 patients. The method showed high accuracy (86% detection, 8.4% false-positive rate) and reproducibility across scanners. The work was supported in part by F. Hoffmann-La Roche — Genentech, the manufacturer of Ocrelizumab. The findings enable reanalysis of existing clinical trial data and may improve future MS research and treatment monitoring.
Set up alerts, explore entity relationships, search across thousands of events, and build custom intelligence feeds.
Open Dashboard