Generative AI fills gaps in brain wiring maps where MRI scans lose signal

Researchers from the Mark and Mary Stevens Neuroimaging and Informatics Institute at the Keck School of Medicine of USC have developed an AI model that helps fill gaps in brain wiring maps made with diffusion MRI scans. This tool could aid researchers in studying how key brain connections change with aging and disease, particularly in areas like the brainstem and orbitofrontal region where MRI scans can lose signal due to distortions in the scanner's magnetic field.

The model, named FOD-Diffusion, uses generative AI to predict missing information based on the surrounding intact tissue and what it has learned from scans without those gaps, ultimately improving the accuracy of the brain wiring maps.

Brief written by urgent.news from Medical Xpress's own syndicated text. Machine-written — may contain errors; check the original before relying on it.