Deep self‐cleansing for medical image segmentation with noisy labels

The proposed deep self-cleansing segmentation framework offers a promising solution to the challenge of noisy labels in medical image segmentation. By integrating a GMM-based LFM and an LCM, the framework effectively preserves clean labels and generates pseudo low-noise labels, thereby improving the overall segmentation accuracy. The successful validation on both clinical and public datasets underscores the potential of this approach to enhance disease diagnosis and surgical planning in medical imaging.

Authors

Institutions

Publication Details

Journal
Medical Physics
Published
2025-09-22
DOI
https://doi.org/10.1002/mp.70007
Primary Topic
Machine Learning and Data Classification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep self‐cleansing for medical image segmentation with noisy labels

Jiahua Dong, S. Kevin Zhou, Yen‐Wei Chen, Shaolin Gong et al.
Medical Physics
Machine Learning and Data Classification
article

Deep self‐cleansing for medical image segmentation with noisy labels

Jiahua Dong, S. Kevin Zhou, Yen‐Wei Chen, Shaolin Gong, Qiuli Wang, Xuanpu Zhang, Lanfen Lin, Yue Zhang, Shihong Ying, Ruofeng Tong
article en

Abstract

The proposed deep self-cleansing segmentation framework offers a promising solution to the challenge of noisy labels in medical image segmentation. By integrating a GMM-based LFM and an LCM, the framework effectively preserves clean labels and generates pseudo low-noise labels, thereby improving the overall segmentation accuracy. The successful validation on both clinical and public datasets underscores the potential of this approach to enhance disease diagnosis and surgical planning in medical imaging.

Medical PhysicsVol. 52(10)
University of Science and Technology of China (CN), Ritsumeikan University (JP), Anhui University (CN), University of Electronic Science and Technology of China (CN), Army Medical University (CN), Zhejiang University of Science and Technology (CN), Chinese Academy of Sciences (CN), Institute of Computing Technology (CN), Suzhou Research Institute (CN), Southwest Hospital (CN), First Affiliated Hospital Zhejiang University (CN), Zhejiang University (CN)
Openalex Percentile: Top 86%
Machine Learning and Data Classification
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Deep self‐cleansing for medical image segmentation with noisy labels — Jiahua Dong, S. Kevin Zhou, et al. · Medical Physics (2025) | TGRS Research Map | TGRS