AI could help detect epilepsy-linked brain lesions that are often missed – study
The software, known as Meld Graph, was developed by scientists at King’s College London and University College London.
Artificial intelligence (AI) could help detect abnormalities in the brain linked to epilepsy that can sometimes be missed by radiologists, according to a study.
Using the technology in this way could lead to earlier diagnosis and better management of the condition, researchers suggest.
The software, known as Meld Graph, was developed by scientists at King’s College London and University College London (UCL).
It was trained to detect focal cortical dysplasia (FCD), malformations that happen when neurons do not develop properly in certain areas of the brain.
These lesions are a common cause of a type of epilepsy that is often drug-resistant.
There are 630,000 people with epilepsy in the UK, the equivalent of about one in every 100.
Of the total, about one in five have epilepsy that is caused by lesions on the brain, which can be treated with surgery.
However, FCDs can be “subtle”, researchers said, and can sometimes be missed by radiologists.
Dr Konrad Wagstyl, of King’s College London, said: “Radiologists are currently inundated with images they have to review.
“Using an AI-powered tool like Meld Graph can support them with their decisions, making the NHS more efficient, speeding time to treatment for patients and relieving them of unnecessary and costly tests and procedures.”
For the study, published in the JAMA Neurology journal, researchers used MRI data from 1,185 patients, including 703 with FCD, from 23 epilepsy centres around the world.
Half of the data was from children.
Meld Graph was then trained using brain scans to detect subtle abnormalities that might otherwise be missed.
Researchers found the tool was able to detect 64% of brain malformations.
The team said the software’s “clinical implementation holds promise for early diagnosis and improved management of focal epilepsy, potentially leading to better patient outcomes”.
Dr Luca Palma, of Bambino Gesu Children’s Hospital in Italy, who was a co-author of the research, said: “Meld Graph identified a subtle lesion missed by many radiologists in a 12-year-old boy who had daily seizures and had tried nine anti-seizure medications with no improvement to his condition.
“This tool could identify patients with surgically operable epilepsy and help with surgical planning – reducing risks, saving money, improving outcomes.”
Meld Graph is not yet clinically available, but the research team has released it as open-source software and is running workshops to train clinicians on how to use it.
Dr Mathilde Ripart, of UCL, said: “One of the highlights for me is hearing from doctors around the world, including the UK, Chile, India and France, have been able to use our tools to help their own patients.”
Great Ormond Street Hospital is one of the institutions taking part.
Professor Helen Cross, consultant epileptologist at Great Ormond Street Hospital, and director of the UCL Great Ormond Street Institute of Child Health, said: “Many of the children I see have experienced years of seizures and investigations before we find a lesion.
“The epilepsy community is searching for ways to speed up diagnosis and treatment.
“Initiatives such as Meld have the potential to rapidly identify abnormalities that can be removed and potentially cure the epilepsy.”
