Automated generation of epilepsy resection mask in pre-operative space

Drug-resistant epilepsy often requires surgery that aims to remove the epileptogenic zone. Post-operative delineation of the resected tissue can be challenging due to the effects of the brain shift. Therefore, most studies use manual approaches to create 3D resection masks, however, this is prohibitively time-consuming for large sample sizes. Furthermore, manual delineation leads to a discrepancy in masks between investigators.

In this talk, I will discuss my approach to automating the resection mask generation and I will compare my results to manually drawn masks. Finally, I will show an interactive report that allows for easy inspection of the resection mask and its anatomical layout.