Australian researchers announced Tuesday that an artificial intelligence tool capable of detecting subtle brain abnormalities that are difficult to detect in children with epilepsy could help patients undergo potentially life-changing surgery more quickly.
According to experts, epilepsy has multiple causes, and approximately three out of ten cases are attributed to structural abnormalities in the brain . However, MRI scans often miss these abnormalities, especially the smallest lesions that may be hidden deep within the brain's folds.
A team led by Royal Melbourne Children's Hospital paediatric neurologist Emma MacDonald-Lowers trained an AI tool on brain scans of children to detect lesions the size of a blueberry, or even smaller.
"These lesions often go unnoticed, and many children are not considered to need surgery," McDonald-Lowers noted during a press conference ahead of the study's publication in the journal Epilepsy.
She explained that "this tool does not replace the need for radiologists or epilepsy specialists. Rather, it is more like a detective who helps piece together the disjointed parts of the image more quickly, enabling the patient to suggest a potentially life-changing surgery."
Among the patients participating in the study who had cortical dysplasia and focal epilepsy, 80 percent had previously undergone an MRI with normal results.
When researchers used the AI tool to analyze both MRI scans and another type of medical test, positron emission tomography (PET), the success rate was 94 percent for one group of tests and 91 percent for the other.
Of the 17 children in the first group, 12 underwent surgery to remove brain lesions, and 11 were cured of seizures, according to the MacDonald-Lowers team at the Murdoch Children's Research Institute.
She noted that "the next step is to test this detection tool in a more realistic hospital setting on new patients who have not previously been diagnosed."
Epilepsy that causes recurrent seizures affects about one in 200 children, and medications are ineffective in about a third of patients.
0 Comments