Region Uncertainty Estimation for Medical Image Segmentation With Noisy Labels

doi:10.1109/TMI.2025.3589058

CSpace

	Region Uncertainty Estimation for Medical Image Segmentation With Noisy Labels
	Han, Kai 1; Wang, Shuhui 2; Chen, Jun 1; Qian, Chengxuan 1; Lyu, Chongwen 1; Ma, Siqi 1; Qiu, Chengjian 3; Sheng, Victor S.4; Huang, Qingming 5; Liu, Zhe 1
	2025-12-01
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN	0278-0062
卷号	44 期号:12 页码:5197-5207
摘要	The success of deep learning in 3D medical image segmentation hinges on training with a large dataset of fully annotated 3D volumes, which are difficult and time-consuming to acquire. Although recent foundation models (e.g., segment anything model, SAM) can utilize sparse annotations to reduce annotation costs, segmentation tasks involving organs and tissues with blurred boundaries remain challenging. To address this issue, we propose a region uncertainty estimation framework for Computed Tomography (CT) image segmentation using noisy labels. Specifically, we propose a sample-stratified training strategy that stratifies samples according to their varying quality labels, prioritizing confident and fine-grained information at each training stage. This sample-to-voxel level processing enables more reliable supervision information to propagate to noisy label data, thus effectively mitigating the impact of noisy annotations. Moreover, we further design a boundary-guided regional uncertainty estimation module that adapts sample hierarchical training to assist in evaluating sample confidence. Experiments conducted across multiple CT datasets demonstrate the superiority of our proposed method over several competitive approaches under various noise conditions. Our proposed reliable label propagation strategy not only significantly reduces the cost of medical image annotation and robust model training but also improves the segmentation performance in scenarios with imperfect annotations, thus paving the way towards the application of medical segmentation foundation models under low-resource and remote scenarios. Code will be available at https://github.com/KHan-UJS/NoisyLabel
关键词	Noise measurement Training Image segmentation Annotations Uncertainty Estimation Medical diagnostic imaging Data models Computational modeling Noise Medical image segmentation noisy label learning uncertainty estimation pseudo label
DOI	10.1109/TMI.2025.3589058
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001631860200019
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42926
专题	中国科学院计算技术研究所
通讯作者	Liu, Zhe
作者单位	1.Jiangsu Univ, Sch Comp Sci & Commun Engn, Zhenjiang 212013, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 3.Huaiyin Normal Univ, Sch Comp Sci & Technol, Huaian 223399, Peoples R China 4.Texas Tech Univ, Dept Comp Sci, Lubbock, TX 79409 USA 5.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Han, Kai,Wang, Shuhui,Chen, Jun,et al. Region Uncertainty Estimation for Medical Image Segmentation With Noisy Labels[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2025,44(12):5197-5207.
APA	Han, Kai.,Wang, Shuhui.,Chen, Jun.,Qian, Chengxuan.,Lyu, Chongwen.,...&Liu, Zhe.(2025).Region Uncertainty Estimation for Medical Image Segmentation With Noisy Labels.IEEE TRANSACTIONS ON MEDICAL IMAGING,44(12),5197-5207.
MLA	Han, Kai,et al."Region Uncertainty Estimation for Medical Image Segmentation With Noisy Labels".IEEE TRANSACTIONS ON MEDICAL IMAGING 44.12(2025):5197-5207.