A team of UCL-led international researchers has developed an AI algorithm that detects the subtle brain abnormalities that cause epileptic seizures.
The algorithm was developed using more than 1,000 patient MRI scans from 22 global epilepsy centres.
The scans reveal where abnormalities are in cases of drug-resistant focal cortical dysplasia (FCD) – a major cause of epilepsy.
These areas of the brain have developed abnormally and often cause drug-resistant epilepsy.
The researchers quantified cortical features from the MRI scans, such as how thick the brain surface was, using around 300,000 locations in the brain.
They then trained the algorithm using examples that had been labelled by expert radiologists as either being healthy of having FCD.
The findings revealed that the algorithm was able to detect FCD in 67 per cent of cases in the cohort of 538 participants.
Previously, the radiologists had been unable to detect the abnormality in 178 participants, yet the algorithm successfully identified FCD in 63 per cent of these.
If doctors are able to find the abnormality, surgery to remove it can cure the condition.
Co-first author, Mathilde Ripart (UCL Great Ormond Street Institute of Child Health), said:
“We put an emphasis on creating an AI algorithm that was interpretable and could help doctors make decisions. Showing doctors how the MELD algorithm made its predictions was an essential part of that process.”
Co-senior author, Dr Konrad Wagstyl (UCL Queen Square Institute of Neurology) added:
“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.
“Roughly 440 children per year could benefit from epilepsy surgery in England.”
Around 1 per cent of the world’s population have epilepsy, with around 600,000 people in the UK affected.
While drug treatments are widely available, 20-30 per cent of people do not respond to medication.
Co-first author, Dr. Hannah Spitzer (Helmholtz Munich) said:
“Our algorithm automatically learns to detect lesions from thousands of MRI scans of patients.
“It can reliably detect lesions of different types, shapes and sizes, and even many of those lesions that were previously missed by radiologists.”
Co-senior author, Dr Sophie Adler (UCL Great Ormond Street Institute of Child Health) added:
“We hope that this technology will help to identify epilepsy-causing abnormalities that are currently being missed.
“Ultimately it could enable more people with epilepsy to have potentially curative brain surgery.”
AI helps cut nuisance alerts for healthcare teams
Stabilising the NHS – it’s going to take a lot more than AI
Answer Digital enables speedy deployment of AI with strategic partnerships
Transforming NHS procurement: How good data holds the key to integrated care
British tech firm gets green light on fibroids patent
Cancer leaders pen ‘letter to the world’ calling for urgent investment
Generative AI used to create translatable paediatric care videos for LMIC hospitals
NHS Forth Valley goes live with RCPCH GrowthAPI integrated with Morse Mobile EPR
Mid and South Essex ICS building new shared care record with Orion Health
Red light can reduce blood glucose levels, study finds
- Research3 weeks ago
3D-printed human brain tissue could advance Alzheimer’s research
- News1 week ago
Don’t miss this final chance to nominate your health tech heroes
- News4 weeks ago
Cutting-edge tech to optimise stereotactic radiosurgery demonstrated live at Arab Health
- AI2 weeks ago
AI helps to predict whether antidepressants will work