AI-enabled image processing reveals invisible cortical lesions in MRI scans of MS patients, advancing diagnosis and research.
Key Details
- 1UB-led team developed AI techniques to visualize gray matter (cortical) lesions in existing MRI scans from MS patients.
- 2Conventional MRI detects only white matter lesions; new AI methods overcome this barrier.
- 3Researchers applied multimodal cortical lesion enhancement (MMCLE) and other techniques on large-scale clinical trial MRI datasets (700+ participants).
- 4AI revealed 15-20 cortical lesions per patient (over 11,000 in total), previously unseen on standard scans.
- 5The findings promise improved assessment of MS progression and cognitive impact.
- 6Collaboration included academic teams and industry support from Genentech.
Why It Matters
This breakthrough dramatically improves the ability to study and monitor MS by making previously undetectable lesions visible, opening avenues for better diagnostics and therapy evaluation. It also enables retrospective analysis of MRI scans from past clinical trials, enhancing research and clinical workflows in neuroimaging.
Source
EurekAlert
Related News
•EurekAlert
Light-Driven Random Number Generators Boost Image Security at Hardware Level
Researchers at Hanyang University developed a light-driven true random number generator for embedding secure signatures into images and detecting tampering.
•EurekAlert
AI Accelerates Radiopharmaceuticals, Boosts Personalized Dosimetry in Cancer
Machine learning is driving advancements in radiopharmaceutical drug discovery and optimizing patient-specific dosimetry for precision cancer therapy.
•EurekAlert
Physicians Overly Trust Erroneous AI, Ignore Contradictory Evidence
Physicians tend to trust incorrect AI advice, even when evidence contradicts it, suggesting risks in clinical decision-making with AI tools.