Projects

Deep Learning based Automated ASPECT Score and Infarct Core Prediction for Stroke Patients

The onset of ischemic stroke can be attributed to large vessel occlusions (LVOs), which lead to insufficient supply of oxygen to brain. Early detection and evaluation of infarct core volume plays a crucial role in the optimal treatment for brain ischemia. Leveraging state of the art Deep Learning techniques on Non-Contrast CT (NCCT) brain scans of patients affected by ischemic stroke, our goals are to 

• automate computing of Alberta Stroke ProgramEarly CT Score (ASPECT Score)
• automate the segmentation of the infarct core
• generate Cerebral Blood Volume (CBV) perfusion maps.