Synergy-Guided Regional Supervision of Pseudo Labels for Semi-Supervised Medical Image Segmentation

TL;DR

This paper presents SGRS-Net, a semi-supervised learning framework for medical image segmentation that improves pseudo label quality by regional supervision guided by synergy evaluation, leading to better performance.

Contribution

The paper introduces a novel synergy-guided regional supervision method for pseudo labels, enhancing semi-supervised segmentation accuracy with a mean teacher network and region-based loss evaluation.

Findings

Outperforms state-of-the-art methods on LA dataset

Effective noise reduction in pseudo labels

Improves segmentation robustness and accuracy

Abstract

Semi-supervised learning has received considerable attention for its potential to leverage abundant unlabeled data to enhance model robustness. Pseudo labeling is a widely used strategy in semi supervised learning. However, existing methods often suffer from noise contamination, which can undermine model performance. To tackle this challenge, we introduce a novel Synergy-Guided Regional Supervision of Pseudo Labels (SGRS-Net) framework. Built upon the mean teacher network, we employ a Mix Augmentation module to enhance the unlabeled data. By evaluating the synergy before and after augmentation, we strategically partition the pseudo labels into distinct regions. Additionally, we introduce a Region Loss Evaluation module to assess the loss across each delineated area. Extensive experiments conducted on the LA dataset have demonstrated superior performance over state-of-the-art techniques, underscoring the efficiency and practicality of our framework.