AI tool detects tiny brain lesions in children with epilepsy

Tiny brain lesions that cause severe epilepsy in children are now being detected with an advanced AI tool, developed by researchers at the Murdoch Children’s Research Institute (MCRI) and The Royal Children’s Hospital (RCH). The tool is expected to lead to faster diagnosis and more precise treatment, according to a study published in the journal Epilepsia.

About one in 200 children has epilepsy, with more than 21,000 children in Victoria living with uncontrolled seizures. Focal cortical dysplasias, which develop when the baby is still in the womb, are a common cause of drug-resistant seizures.

“The seizures usually start out of the blue during the preschool or early school years before escalating to multiple times a day,” explained MCRI’s Dr Emma Macdonald-Laurs, who led the team that created the AI tool.

“Children often need to attend the emergency department or be admitted to hospital for treatment. Over time, frequent seizures impact on a child’s behaviour, mood and ability to learn.

“Epilepsy due to cortical dysplasia can, however, be improved or cured with epilepsy surgery if the abnormal brain tissue can be located and removed.”

But Macdonald-Laurs said cortical dysplasias are hard to spot on routine MRIs, with less than half of these blueberry-sized lesions being recognised on a child’s first scan.

“Cortical dysplasias can be impossible for traditional MRI techniques to identify,” she said. “Failure to locate the abnormal tissue slows the pathway to a definitive diagnosis and may stop a child being referred for potentially curative epilepsy surgery.

“The longer a child continues to have uncontrolled seizures, the more likely they are to develop learning difficulties, including intellectual disability.”

The MCRI-led study involved 71 children at the RCH and 23 adults at the Austin Hospital with cortical dysplasia and focal epilepsy, which causes recurring seizures. Before using the AI detector’s keen eye, the study found 80% of patients had their diagnosis missed by human examination of their MRI results.

MRI and FDG-positron emission tomography (FDG-PET scans) were used to train the AI detector, with children separated into training and test cohorts. A separate group of adult scans was used for additional validation of the detector’s performance.

Using information from both MRI and PET scans, the best result was recorded in the test cohort with a success rate of 94%. Of the 17 children in the test group, 12 had surgery and 11 are now seizure free.

With additional funding, Macdonald-Laurs said the detector could be tested in paediatric hospitals across Australia. She noted that more accurate diagnosis of cortical dysplasia would lead to faster referrals for epilepsy surgery, fewer seizures and improved long-term developmental outcomes.

“With more accurate imaging, neurosurgeons can develop a safer surgical roadmap to avoid important blood vessels and brain regions that control speech, thinking and movement and removing healthy brain tissue,” she said. “Children also avoid the need to have to undergo invasive testing.”

Image credit: iStock.com/Martinbowra