LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation
文献类型：期刊论文
| 作者 | Zhao, Ziyuan3,4,5; Zhou, Fangcheng6,7; Xu, Kaixin4; Zeng, Zeng1,4; Guan, Cuntai3; Zhou, S. Kevin2,8 |
| 刊名 | IEEE TRANSACTIONS ON MEDICAL IMAGING
 |
| 出版日期 | 2023-03-01 |
| 卷号 | 42期号:3页码:633-646 |
| ISSN号 | 0278-0062 |
| 关键词 | Image segmentation Adaptation models Biomedical imaging Annotations Adversarial machine learning Magnetic resonance imaging Training Unsupervised domain adaptation medical image segmentation cross-modality learning semi-supervised learning adversarial learning |
| DOI | 10.1109/TMI.2022.3214766 |
| 英文摘要 | While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the expert-driven and time-consuming nature of pixel-level annotations in clinical practices, and (ii) failure to generalize from one domain to another, especially when the target domain is a different modality with severe domain shifts. Recent unsupervised domain adaptation (UDA) techniques leverage abundant labeled source data together with unlabeled target data to reduce the domain gap, but these methods degrade significantly with limited source annotations. In this study, we address this underexplored UDA problem, investigating a challenging but valuable realistic scenario, where the source domain not only exhibits domain shift w.r.t. the target domain but also suffers from label scarcity. In this regard, we propose a novel and generic framework called "Label-Efficient Unsupervised Domain Adaptation " (LE-UDA). In LE-UDA, we construct self-ensembling consistency for knowledge transfer between both domains, as well as a self-ensembling adversarial learning module to achieve better feature alignment for UDA. To assess the effectiveness of our method, we conduct extensive experiments on two different tasks for cross-modality segmentation between MRI and CT images. Experimental results demonstrate that the proposed LE-UDA can efficiently leverage limited source labels to improve cross-domain segmentation performance, outperforming state-of-the-art UDA approaches in the literature. |
| WOS研究方向 | Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000971629600006 |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/21457]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zeng, Zeng; Guan, Cuntai |
| 作者单位 | 1.Shanghai Univ, Sch Microelect, Shanghai 200444, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 100190, Singapore 4.ASTAR, Inst Infocomm Res I2R, Singapore 138632, Singapore 5.ASTAR, Artificial Intelligence Analyt & Informat AI3, Singapore 138632, Singapore 6.ASTAR, I2R, Singapore, Singapore 7.Natl Univ Singapore, Dept Math, Singapore 119076, Singapore 8.Univ Sci & Technol China, Suzhou Inst Adv Res, Sch Biomed Engn, Ctr Med Imaging Robot Analyt Computing & Learning, Suzhou 215123, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Ziyuan,Zhou, Fangcheng,Xu, Kaixin,et al. LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,42(3):633-646. |
| APA | Zhao, Ziyuan,Zhou, Fangcheng,Xu, Kaixin,Zeng, Zeng,Guan, Cuntai,&Zhou, S. Kevin.(2023).LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation.IEEE TRANSACTIONS ON MEDICAL IMAGING,42(3),633-646. |
| MLA | Zhao, Ziyuan,et al."LE-UDA: Label-Efficient Unsupervised Domain Adaptation for Medical Image Segmentation".IEEE TRANSACTIONS ON MEDICAL IMAGING 42.3(2023):633-646. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。