Automatic segmentation of abdominal aortic aneurysms from CT angiography using a context-aware cascaded U-Net

Nan Mu, Zonghan Lyu, Mostafa Rezaeitaleshmahalleh, Xiaoming Zhang, Todd Rasmussen, Robert McBane, Jingfeng Jiang

Abstract: Highlights•This paper aims to automatically segment abdominal aortic aneurysm from CTA images.•Two-stage context-aware cascaded U-Net is designed to capture surrounding context.•An auto-context algorithm involving deep supervision at different resolutions.•An anisotropic context module is used to capture short and long rang dependency.•A rebalancing multi-class loss is explored to handle severely imbalanced classes.