An artificial intelligence (AI) algorithm that can spot tiny brain irregularities that cause epileptic seizures has been developed by a multidisciplinary research team headed by UCL. The Multicentre Epilepsy Lesion Detection project (MELD) algorithm was created using more than 1,000 patient MRI scans from 22 international epilepsy centres. The algorithm reports the locations of abnormalities in cases of drug-resistant focal cortical dysplasia (FCD), a major cause of epilepsy.
As a result of incorrect evolution, brain areas called FCDs frequently cause drug-resistant epilepsy. Surgery is typically used to treat it, however because MRI scans for FCDs can look normal, clinicians frequently struggle to spot the lesions on the scans.
To assess cortical features from the MRI scans, such as how thick or folded the cortex/brain surface was, the researchers used roughly 300,000 locations throughout the brain.
Then, using the cases that professional radiologists had identified as either having FCD or having a healthy brain using their patterns and characteristics, the system was trained.
The findings, which were published in Brain, show that generally the algorithm was successful in recognising the FCD in 67 percent of occurrences in the group (538 participants).
Senior author Dr. Konrad Wagstyl from the UCL Queen Square Institute of Neurology added “This algorithm might make it easier to identify these concealed lesions in epileptic children and adults, which would increase the number of patients who could potentially benefit from brain surgery to treat their condition and enhance cognitive function. In England, epilepsy surgery could help about 440 kids a year.”
Recurrent seizures are the hallmark of epilepsy, a serious neurological condition that affects 1% of the global population.
In the UK, the affected population is roughly 600,000. Pharmaceuticals can be used to treat most epilepsy patients, however 20–30% of them do not respond well to them.
