Neuroanatomic markers of post-traumatic epilepsy based on magnetic resonance imaging and machine learning

Although post-traumatic epilepsy (PTE) is a common complication of traumatic brain injury (TBI), the relationship between these conditions is unclear, early PTE detection and prevention being major unmet clinical challenges. This study aims to identify imaging biomarkers that distinguish PTE and non-PTE subjects among TBI survivors based on a magnetic resonance imaging (MRI) dataset. We performed tensor-based morphometry to analyze brain shape changes associated with TBI and to derive imaging features for statistical group comparison. Additionally, machine learning was used to identify structural anomalies associated with brain lesions. Automatically generated brain lesion maps were used to identify brain regions where lesion load may indicate an increased incidence of PTE. Statistical analysis suggests that lesions in the temporal lobes, cerebellum, and the right occipital lobe are associated with an increased PTE incidence.