Machine Learning Could Help The Diagnosis of Drug-Resistant Epilepsy

‘Machine learning’, a type of computer modelling, can detect areas of brain damage (lesions) associated with drug-resistant epilepsy. This is according to a new study published in the scientific journal PLOS One. During the study, researchers led by Dr Carole Lartizien, from the University of Lyon, developed a complex system that is able learn features associated with healthy brain MRI scans. It can then be used to assess other MRI scans for abnormalities (i.e. how much they deviate from the normal ‘patterns’ it has learned). The scientists focused on two parameters, detectable on MRI images, that are associated with lesions linked to epilepsy. These are the presence of grey matter within the white matter (heterotopia), and a blurred junction between grey and white matter. Dr Lartizien and her team tested the performance of the system on brain MRI images from 11 people with drug-resistant…


Link to Full Article: Machine Learning Could Help The Diagnosis of Drug-Resistant Epilepsy