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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Guanghao, Zhang, Jing, Liu, Juanxiu, Du, Xiaohui, Hao, Ruqian, Liu, Yong, Liu, Lin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910505857187840
author Zhu, Guanghao
Zhang, Jing
Liu, Juanxiu
Du, Xiaohui
Hao, Ruqian
Liu, Yong
Liu, Lin
author_facet Zhu, Guanghao
Zhang, Jing
Liu, Juanxiu
Du, Xiaohui
Hao, Ruqian
Liu, Yong
Liu, Lin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AstMatch: Adversarial Self-training Consistency Framework for Semi-Supervised Medical Image Segmentation
Zhu, Guanghao
Zhang, Jing
Liu, Juanxiu
Du, Xiaohui
Hao, Ruqian
Liu, Yong
Liu, Lin
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title AstMatch: Adversarial Self-training Consistency Framework for Semi-Supervised Medical Image Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.19649