A new artificial intelligence algorithm may help cure epilepsy. Researchers from the University College London developed an algorithm that can detect subtle brain abnormalities which cause epileptic seizures.
The Multicenter Epilepsy Lesion Detection (MELD) project developed the algorithm by using over 1,000 patient MRI scans from 22 global epilepsy centers. The algorithm provides reports of where abnormalities are in cases of drug-resistant focal cortical dysplasia (FCD), which is a leading cause of epilepsy.
Researchers say FCDs are areas of the brain that have developed abnormally and usually cause drug-resistant epilepsy. FCDs are mainly treated with surgery, but identifying the lesions from an MRI is a problem for clinicians. MRI scans in FCDs can look normal.
Study authors developed the algorithm by quantifying cortical features from MRI scans, including how thick or folded the cortex/brain surface was. Around 300,000 locations across the brain were used. Researchers then trained the algorithm on examples labeled by radiologists as either being a healthy brain or having FCD.
The algorithm was able to detect the FCD in 67 percent of cases among 538 participants. Previously, radiologists weren’t able to find the abnormality in 178 of the participants, but the MELD algorithm was able to identify the FCD in 63 percent of those cases.
If doctors can find the abnormality in the brain scan, then surgery to remove the FCD can provide a cure for epilepsy.
“We put an emphasis on creating an AI algorithm that was interpretable and could help doctors make decisions,” says study co-author Mathilde Ripart, of the UCL Great Ormond Street Institute of Child Health, in a media release. “Showing doctors how the MELD algorithm made its predictions was an essential part of that process.”
Dr. Konrad Wagstyl, study co-senior author at the UCL Queen Square Institute of Neurology, says hundreds of children could benefit from epilepsy surgery thanks to this new AI algorithm. “This algorithm could help to find more of these hidden lesions in children and adults with epilepsy, and enable more patients with epilepsy to be considered for brain surgery that could cure the epilepsy and improve their cognitive development,” explains Dr. Wagstyl. “Roughly 440 children per year could benefit from epilepsy surgery in England.”
FCD is the most common cause in children who have had surgery to control their epilepsy. Among adults, FCD is the third most common cause. Researchers say FCD is also the most common cause for epileptic patients who have an abnormality in the brain that cannot be found on MRI scans.
“Our algorithm automatically learns to detect lesions from thousands of MRI scans of patients,” notes study co-first author Dr. Hannah Spitzer, of Helmholtz Munich. “It can reliably detect lesions of different types, shapes and sizes, and even many of those lesions that were previously missed by radiologists.”
The FCD detection study uses the largest MRI cohort of FCDs, meaning it is able to detect all types of FCD. Researchers say the MELD FCD classifier tool can be run on any patient with a suspicion of having an FCD who is over the age of 3 and has an MRI scan.
“We hope that this technology will help to identify epilepsy-causing abnormalities that are currently being misses,” says study co-senior author Dr. Sophie Adler, of the UCL Great Ormond Street Institute of Child Health. “Ultimately it could enable more people with epilepsy to have potentially curative brain surgery.”
The study is published in the journal Brain.
