London: Led a multinational research team UCL has developed an artificial intelligence (AI) program that can recognize min the brain Abnormalities that lead to epileptic seizures.
Algorithm used in Multicenter Epilepsy Lesion Detection Project (MELD), drug-resistant focal cortical dysplasia (FCD), the main cause of WiIt was developed using MRI scans of more than 1,000 patients from 22 international epilepsy centers.
Areas of the brain known as FCDs develop improperly and often lead to drug-resistant epilepsy. Surgery is usually used to treat it, however, finding the lesions on MRI is a constant problem for doctors because MRI scans for FCDs can appear normal.
The scientists used about 300,000 locations throughout the brain to measure cortical properties from the MRI scans, such as how thick or folded the cortex/brain surface was.
The system was then trained on cases that experienced radiologists classified as having FCD or healthy brains based on their patterns and features.
Overall, the algorithm was successful in identifying FCD in 67% of cases in the cohort, according to results published in Brain (538 participants).
Radiologists had previously been unable to detect abnormalities in 178 patients based on their MRI results; However, the MELD algorithm was able to detect FCD in 63% of these cases.
This is crucial because, if doctors can identify the anomaly in a brain scan, surgery to remove it can result in recovery.
Mathilde RepartThe co-first author, from UCL Great Ormond Street Institute of Child Health, said: “We focused on developing an AI system that was interpretable and could help clinicians make decisions. A crucial step in that process was showing doctors how MELD The algorithm generates its predictions.
Co-senior author Dr. Konrad Wagstill added: “This algorithm could make it easier to identify these hidden lesions in epileptic children and adults, potentially increasing the number of patients who could benefit from brain surgery to treat their condition and enhance cognitive function. In England, epilepsy surgery in the year can help around 440 children.”
Epilepsy is a serious neurological disease that affects 1% of the world’s population and is marked by frequent seizures.
Around 600,000 people in the UK are affected. Most epilepsy patients can be treated with pharmaceuticals, although 20-30% of them do not benefit.
FCD is the most frequent cause in children who have surgery to treat their epilepsy, and it is the third most frequent cause in adults.
In addition, FCD is the most frequent cause of epilepsy in people who have brain abnormalities that cannot be seen on MRI scans.
Co-first author Dr Hanna Spitzer of Helmholtz Munich said: “Our system automatically learns to detect lesions from thousands of patient MRI scans. It is able to accurately identify lesions of various types, shapes and sizes, including some radiologists. Previously overlooked did
Co-senior author Dr, from the Great Ormond Street Institute of Child Health at University College London. Sophie Adler added: “We believe this technology can help detect the now-missed abnormalities that cause epilepsy. In the long term, it could make it possible for more epilepsy patients to undergo potentially curative brain surgery.”
This FCD detection study uses the largest MRI cohort of FCD to date, enabling it to identify all FCD subtypes.
Study limitations
The 22 hospitals involved in the study used different MRI scanners from around the world, which makes the algorithm more robust but may also affect its sensitivity and specificity.
