Nested resolution mesh-graph CNN for automated extraction of liver surface anatomical landmarks

Xukun Zhang, Jinghui Feng, Peng Liu, Minghao Han, Yanlan Kang, Jingyi Zhu, Le Wang, Xiaoying Wang, Sharib Ali, Lihua Zhang

Abstract: Highlights•A novel nested-resolution Mesh-Graph CNN is proposed for liver landmark segmentation.•Combines global shape analysis with local topological refinement for accuracy.•An attention fusion module with auxiliary supervision enhances spatial consistency.•200 annotated liver meshes were used to develop and validate the proposed method.•Experiments show superior performance over state-of-the-art segmentation methods.

External IDs:dblp:journals/mia/ZhangFLHKZWWAZ26