AstMatch: Adversarial Self-training Consistency Framework for Semi-Supervised Medical Image Segmentation

TL;DR

AstMatch introduces an adversarial self-training framework for semi-supervised medical image segmentation, combining high-level and low-level consistency regularization with adaptive pseudo-labeling to improve performance.

Contribution

The paper proposes a novel adversarial self-training consistency framework (AstMatch) that enhances pseudo-label reliability and knowledge transfer in semi-supervised medical image segmentation.

Findings

Outperforms existing SSL methods on three datasets.

Achieves state-of-the-art performance with various labeled ratios.

Effectively incorporates high-level and low-level consistency regularization.

Abstract

Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SSL approaches only pay attention to low-level consistency and overlook the significance of pseudo-label reliability. Therefore, in this work, we propose an adversarial self-training consistency framework (AstMatch). Firstly, we design an adversarial consistency regularization (ACR) approach to enhance knowledge transfer and strengthen prediction consistency under varying perturbation intensities. Second, we apply a feature matching loss for adversarial training to incorporate high-level consistency regularization. Additionally, we present the pyramid channel attention (PCA) and efficient channel and spatial attention (ECSA) modules to improve the discriminator's performance. Finally, we propose an adaptive self-training (AST) approach to ensure the pseudo-labels' quality. The proposed AstMatch has been extensively evaluated with cutting-edge SSL methods on three public-available datasets. The experimental results under different labeled ratios indicate that AstMatch outperforms other existing methods, achieving new state-of-the-art performance. Our code will be available at https://github.com/GuanghaoZhu663/AstMatch.