MONDAY, Oct. 6, 2025 (HealthDay News) -- Detection of bottom-of-sulcus dysplasia (BOSD) is better with an automated detector combining fluorodeoxyglucose positron emission tomography (FDG-PET) with magnetic resonance imaging (MRI) features, according to a study published online Sept. 30 in Epilepsia.Emma Macdonald-Laurs, M.B.Ch.B., Ph.D., from Royal Children's Hospital in Parkville, Australia, and colleagues reported the development and performance of an automated BOSD detector using combined MRI+PET in a training set of 54 patients with focal epilepsy and BOSD and in test sets including 17 subsequently diagnosed patients with BOSD from the same center and 12 published patients from a different center. Overall, 81 percent of patients across the training and test sets had normal initial MRIs; most BOSDs were <1.5 cm3. To determine which features best distinguish a dysplastic from normal-appearing cortex, 12 features were evaluated from T1-MRI, fluid-attenuated inversion recovery-MRI, and FDG-PET in the training set. Neural network classifiers were then trained and tested on MRI+PET, MRI-only, and PET-only features.The researchers found that compared with MRI features, cortical and subcortical hypometabolism on FDG-PET was superior in discriminating a dysplastic from normal-appearing cortex. When the BOSD detector was trained on MRI+PET features, 87, 94, and 75 percent of BOSDs were overlapped by one of the top five clusters in the training, prospective test, and published test sets, respectively (69, 88, and 58 percent in the top cluster). When the detector was trained and tested on PET-only or MRI-only features, cluster overlap was generally lower."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," Macdonald-Laurs said in a statement.Abstract/Full Text (subscription or payment may be required).Sign up for our weekly HealthDay newsletter