Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning

TL;DR

This paper introduces a novel self-supervised instance-adaptive prototype learning approach for medical image segmentation, addressing intra-class variation and sample diversity to improve segmentation accuracy.

Contribution

It proposes generating instance-specific prototypes with a hierarchical transformer-guided confidence re-weighting and a self-supervised filtering strategy, advancing prototype learning in MIS.

Findings

Favorable performance demonstrated on extensive experiments.

Improved handling of intra-class variation.

Enhanced segmentation accuracy over existing methods.

Abstract

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.