Multi-annotation agreement and prediction consistency networks: Improving semi-supervised segmentation of medical images with ambiguous boundaries

Shuai Wang, Tengjin Weng, Jingyi Wang, Kai Zhao, Yang Shen, Zhidong Zhao, Yixiu Liu, Pengfei Jiao, Zhiming Cheng, Yaoqi Sun, Yaqi Wang

Abstract: Highlights•We propose MSE-Nets combining multi-annotated and semi-supervised segmentation.•We propose NPCE to separate pixel-level agreement and disagreement for label refinement.•We design MNPS to use multi-network consistency for robust learning from unlabeled data.

External IDs:dblp:journals/artmed/WangWWZSZLJCSW26