Machine Learning-Based Lateralization of Mesial Temporal Lobe Epilpepsy Using ASL MRI

Motivation: Utilizing perfusion features to differentiate left and right mesial temporal lobe epilepsy (mTLE) using machine learning. Goal(s): The study aims to assess ASL MRI's perfusion analysis ability to identify abnormalities in brain regions for distinguishing between mTLE cases and normal cohorts. Approach: Cerebral blood flow obtained features used by different machine learning classifiers to separate right and left mTLE form control cohort. Results: The utilization of CBF features proved valuable and effective in the machine learning-based classification of right and left mTLE data from the control cohort. Impact: This study's outcomes benefit medical professionals and drug-resistant mTLE patients by expediting surgical assessments and enhancing treatment outcomes through improved lateralization and epilepsy classification.