AI Tool Detects Tiny Brain Lesions in Children with Epilepsy

Strategic Insights -

A team of researchers at the Murdoch Children's Research Institute (MCRI) and The Royal Children's Hospital (RCH) has developed an AI tool that can detect tiny brain lesions causing severe epilepsy in children. According to a new study published in Epilepsia, the tool can find lesions the size of a blueberry in up to 94% of cases with the support of medical imaging.

Key Takeaways:

  • The AI tool, developed by MCRI and RCH, can detect focal cortical dysplasias, a common cause of drug-resistant seizures in children, with a success rate of 94%.
  • The study involved 71 children at RCH and 23 adults at the Austin Hospital, and found that before using the AI detector, 80% of patients had their diagnosis missed by human examination of their MRI results.
  • The AI tool uses information from both MRI and PET scans to detect the lesions, and has been validated in a separate group of adult scans.
  • Of the 17 children in the test group, 12 had surgery and 11 are now seizure-free.
  • Cortical dysplasias can be impossible for traditional MRI techniques to identify, and 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 team plans to test the detector in pediatric hospitals across Australia with additional funding.

Statistics:

  • 94% success rate in detecting focal cortical dysplasias with the AI tool
  • 80% of patients had their diagnosis missed by human examination of their MRI results before using the AI detector
  • 17 children in the test group, of which 12 had surgery and 11 are now seizure-free
  • 1 in 200 children has epilepsy
  • Cortical dysplasias develop when the baby is still in the womb and can cause drug-resistant seizures

Sources:

  • Emma Macdonald-Laurs, Aaron E.L. Warren, Remika Mito, Sila Genc, Bonnie Alexander, Sarah Barton, Joseph Yuan-Mou Yang, Peter Francis, Heath R. Pardoe, Graeme Jackson and A. Simon Harvey. 'Automated detection of bottom-of-sulcus dysplasia on MRI-PET in patients with drug-resistant focal epilepsy,' Epilepsia. DOI: 10.1111/epi.18628
  • NewsRx, October 18, 2025, Pediatrics Week