Exploring Large Context for Cerebral Aneurysm Segmentation

Automated segmentation of aneurysms from 3D CT is important for the diagnosis, monitoring, and treatment planning cerebral aneurysm disease. This short paper briefly presents main technique details method in MICCAI 2020 CADA challenge. The contribution that we configure U-Net with a large patch size, which can obtain context. Our ranked second on testing dataset an average Jaccard 0.7593. code trained models are publicly available at https://github.com/JunMa11/CADA2020.