Automatic segmentation of intraluminal thrombosis of abdominal aortic aneurysms from CT angiography using a mixed-scale-driven multiview perception network (M2Net) model

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

Abstract: Highlights•This paper proposes a mixed-scale multiview pipeline for accurate ILT segmentation.•Mixed-scale 2D CNN is used to extract information from three orthogonal views.•We leveraged multiview information to enrich prior knowledge for 3D ILT learning.•We designed a context-aware CNN to fully integrate multiview ILT-related objects.