Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation
IEEE Transactions on Medical Imaging · 2025
DOI: 10.1109/tmi.2025.3575162 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Qinghe Ma und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Supervised Machine Learning, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Science and Technology Major Project, NSFC Project, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS), where limited labeled data from a single domain and a large amount of unlabeled data from multiple domains. To tackle this issue, we propose the UST-RUN framework, which fully leverages intermediate domain information to facilitate knowledge transfer. We employ Unified Copy-paste (UCP) to construct intermediate domains, and propose a Symmetric GuiDance training strategy (SymGD) to supervise unlabeled data by merging pseudo-labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progressively incorporate style-transition components into intermediate samples. To generate more diverse intermediate samples, we further select reliable samples with high-quality pseudo-labels, which are then mixed with other unlabeled data. Additionally, we generate sophisticated intermediate samples with high-quality pseudo-labels for unreliable samples, ensuring effective knowledge transfer for them. Extensive experiments on four public datasets demonstrate the superiority of UST-RUN. Notably, UST-RUN achieves a 12.94% improvement in Dice score on the Prostate dataset. Our code is available at https://github.com/MQinghe/UST-RUN.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Science and Technology Major Project
- NSFC Project
- China Postdoctoral Science Foundation
- Fundamental Research Funds for the Central Universities
- State Key Laboratory Fund
- Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
- Jiangsu Funding Program for Excellent Postdoctoral Talent
- Jiangsu Science and Technology Major Project
Zitieren
APA
Ma, Q., Zhang, J., Qi, L., Yu, Q., Shi, Y., & Gao, Y. (2025). Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3575162
Vancouver
Ma Q, Zhang J, Qi L, Yu Q, Shi Y, Gao Y. Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3575162
BibTeX
@article{Ma2025,
author = {Ma, Qinghe and Zhang, Jian and Qi, Lei and Yu, Qian and Shi, Yinghuan and Gao, Yang},
title = {Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
doi = {10.1109/tmi.2025.3575162}
}
EUVIMED