Consistency and adversarial semi-supervised learning for medical image segmentation

被引:9
作者
Tang, Yongqiang [2 ]
Wang, Shilei [1 ]
Qu, Yuxun
Cui, Zhihua [1 ,3 ]
Zhang, Wensheng [2 ]
机构
[1] Taiyuan Univ Sci & Technol, Sch Comp Sci & Technol, Taiyuan 030024, Shanxi, Peoples R China
[2] Chinese Acad Sci, Inst Automation, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
[3] Nankai Univ, Coll Comp Sci, Tianjin 300350, Peoples R China
基金
中国国家自然科学基金;
关键词
Medical image segmentation; Semi-supervised learning; Mean teacher; Adversarial learning; Deep neural network;
D O I
10.1016/j.compbiomed.2023.107018
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Medical image segmentation based on deep learning has made enormous progress in recent years. However, the performance of existing methods generally heavily relies on a large amount of labeled data, which are commonly expensive and time-consuming to obtain. To settle above issue, in this paper, a novel semi-supervised medical image segmentation method is proposed, in which the adversarial training mechanism and the collaborative consistency learning strategy are introduced into the mean teacher model. With the adversarial training mechanism, the discriminator can generate confidence maps for unlabeled data, such that more reliable supervised information for the student network is exploited. In the process of adversarial training, we further propose a collaborative consistency learning strategy by which the auxiliary discriminator can assist the primary discriminator in achieving supervised information with higher quality. We extensively evaluate our method on three representative yet challenging medical image segmentation tasks: (1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 dataset; (2) optic cup and optic disk (OC/OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) dataset; and (3) tumor segmentation from lower-grade glioma (LGG) tumors images. The experimental results validate the superiority and effectiveness of our proposal when compared with the state-of-the-art semi-supervised medical image segmentation methods.
引用
收藏
页数:10
相关论文
共 50 条
[31]   Semi-Supervised Learning With Fact-Forcing for Medical Image Segmentation [J].
Bui, Phuoc-Nguyen ;
Le, Duc-Tai ;
Bum, Junghyun ;
Kim, Seongho ;
Song, Su Jeong ;
Choo, Hyunseung .
IEEE ACCESS, 2023, 11 :99413-99425
[32]   Co-Manifold learning for semi-supervised medical image segmentation [J].
Peiris, Himashi ;
Chen, Zhaolin ;
Egan, Gary ;
Harandi, Mehrtash .
NEUROCOMPUTING, 2025, 639
[33]   Multi-consistency for semi-supervised medical image segmentation via diffusion models [J].
Chen, Yunzhu ;
Liu, Yang ;
Lu, Manti ;
Fu, Liyao ;
Yang, Feng .
PATTERN RECOGNITION, 2025, 161
[34]   Semi-supervised Medical Image Segmentation with Strong/Weak Task-Aware Consistency [J].
Wang, Hua ;
Liu, Linwei ;
Lin, Yiming ;
Hu, Jingfei ;
Zhang, Jicong .
PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT XIV, 2025, 15044 :17-31
[35]   Consistency-Guided Differential Decoding for Enhancing Semi-Supervised Medical Image Segmentation [J].
Zeng, Qingjie ;
Xie, Yutong ;
Lu, Zilin ;
Lu, Mengkang ;
Zhang, Jingfeng ;
Xia, Yong .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2025, 44 (01) :44-56
[36]   Dual-scale enhanced and cross-generative consistency learning for semi-supervised medical image segmentation [J].
Gu, Yunqi ;
Zhou, Tao ;
Zhang, Yizhe ;
Zhou, Yi ;
He, Kelei ;
Gong, Chen ;
Fu, Huazhu .
PATTERN RECOGNITION, 2025, 158
[37]   An Evidential-Enhanced Tri-Branch Consistency Learning Method for Semi-Supervised Medical Image Segmentation [J].
Zhang, Zhenxi ;
Zhou, Heng ;
Shi, Xiaoran ;
Ran, Ran ;
Tian, Chunna ;
Zhou, Feng .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73
[38]   Deep semi-supervised learning for medical image segmentation: A review [J].
Han, Kai ;
Sheng, Victor S. ;
Song, Yuqing ;
Liu, Yi ;
Qiu, Chengjian ;
Ma, Siqi ;
Liu, Zhe .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 245
[39]   Stable self-attention adversarial learning for semi-supervised semantic image segmentation [J].
Zhang, Jia ;
Li, Zhixin ;
Zhang, Canlong ;
Ma, Huifang .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2021, 78
[40]   Medical Image Segmentation Using Semi-supervised Conditional Generative Adversarial Nets [J].
Liu S.-P. ;
Hong J.-M. ;
Liang J.-P. ;
Jia X.-P. ;
Ouyang J. ;
Yin J. .
Ruan Jian Xue Bao/Journal of Software, 2020, 31 (08) :2588-2602