文献类型：会议论文

英文题名：Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning

作者：Liang, Guoyan[1];Zhou, Qin[2];Chen, Jingyuan[1];Wang, Zhe[2];Yao, Chang[1]

机构：[1]Zhejiang Univ, Hangzhou, Peoples R China;[2]East China Univ Sci & Technol, Shanghai, Peoples R China

会议论文集：33rd International Joint Conference on Artificial Intelligence (IJCAI)

会议日期：AUG 03-09, 2024

会议地点：Jeju, SOUTH KOREA

语种：英文

摘要：Medical Image Segmentation (MIS) plays a crucial role in medical therapy planning and robot navigation. Prototype learning methods in MIS focus on generating segmentation masks through pixel-to-prototype comparison. However, current approaches often overlook sample diversity by using a fixed prototype per semantic class and neglect intra-class variation within each input. In this paper, we propose to generate instance-adaptive prototypes for MIS, which integrates a common prototype proposal (CPP) capturing common visual patterns and an instance-specific prototype proposal (IPP) tailored to each input. To further account for the intra-class variation, we propose to guide the IPP generation by re-weighting the intermediate feature map according to their confidence scores. These confidence scores are hierarchically generated using a transformer decoder. Additionally we introduce a novel self-supervised filtering strategy to prioritize the foreground pixels during the training of the transformer decoder. Extensive experiments demonstrate favorable performance of our method.