AI algorithm detects brain abnormalities, could help treat epilepsy

An artificial intelligence-based algorithm was able to provide reports of brain abnormalities in cases of drug-resistant focal cortical dysplasia, a leading cause of epilepsy, researchers reported in Brain.

Mathilde Ripart, a research assistant in the department of developmental neuroscience at University College London Great Ormond Street Institute of Child Health, and colleagues quantified cortical features of 1,015 MRI scans from 22 global epilepsy centers to develop the algorithm. They included 538 patients with focal cortical dysplasia epilepsy and 373 controls in the study, known as the Multicenter Epilepsy Lesion Detection project.

The researchers reported that the algorithm detected focal cortical dysplasia in 67% of the 538 cases. Prior to using the algorithm, 178 participants had been considered MRI negative, which meant a radiologist was unable to find an abnormality. Of those, the algorithm detected an abnormality in 63%.

“We put an emphasis on creating an AI algorithm that was interpretable and could help doctors make decisions,” Ripart said in a university release. “Showing doctors how the algorithm made its predictions was an essential part of that process.”

According to study co-author Sophie Adler, PhD, a research fellow at the university, the algorithm could enable those with epilepsy to have potentially curative brain surgery.

“We hope that this technology will help to identify epilepsy-causing abnormalities that are currently being missed,” Adler said in the release.

Reference:

• AI algorithm that detects brain abnormalities could help cure epilepsy. https://www.ucl.ac.uk/news/2022/aug/ai-algorithm-detects-brain-abnormalities-could-help-cure-epilepsy. Published Aug. 12, 2022. Accessed Aug. 12, 2022