Effective Semi-Supervised Medical Image Segmentation With Probabilistic Representations and Prototype Learning
IEEE Transactions on Medical Imaging · 2025-03 · 44 (3) · 1181-1193
DOI: 10.1109/tmi.2024.3484166 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-03. Verfasst von Yuchen Yuan und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Supervised Machine Learning, Diagnostic Imaging. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Grants Council of the Hong Kong Special Administrative Region, China, Hong Kong Innovation and Technology Fund, National Natural Science Foundation of China.
Abstract (Originalsprache)
Label scarcity, class imbalance and data uncertainty are three primary challenges that are commonly encountered in the semi-supervised medical image segmentation. In this work, we focus on the data uncertainty issue that is overlooked by previous literature. To address this issue, we propose a probabilistic prototype-based classifier that introduces uncertainty estimation into the entire pixel classification process, including probabilistic representation formulation, probabilistic pixel-prototype proximity matching, and distribution prototype update, leveraging principles from probability theory. By explicitly modeling data uncertainty at the pixel level, model robustness of our proposed framework to tricky pixels, such as ambiguous boundaries and noises, is greatly enhanced when compared to its deterministic counterpart and other uncertainty-aware strategy. Empirical evaluations on three publicly available datasets that exhibit severe boundary ambiguity show the superiority of our method over several competitors. Moreover, our method also demonstrates a stronger model robustness to simulated noisy data. Code is available at https://github.com/IsYuchenYuan/PPC.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Research Grants Council of the Hong Kong Special Administrative Region, China
- Hong Kong Innovation and Technology Fund
- National Natural Science Foundation of China
Zitieren
APA
Yuan, Y., Wang, X., Yang, X., & Heng, P. A. (2025). Effective Semi-Supervised Medical Image Segmentation With Probabilistic Representations and Prototype Learning. IEEE Transactions on Medical Imaging, 44(3), 1181-1193. https://doi.org/10.1109/tmi.2024.3484166
Vancouver
Yuan Y, Wang X, Yang X, Heng PA. Effective Semi-Supervised Medical Image Segmentation With Probabilistic Representations and Prototype Learning. IEEE Transactions on Medical Imaging. 2025;44(3):1181-1193. doi:10.1109/tmi.2024.3484166
BibTeX
@article{Yuan2025,
author = {Yuan, Yuchen and Wang, Xi and Yang, Xikai and Heng, Pheng-Ann},
title = {Effective Semi-Supervised Medical Image Segmentation With Probabilistic Representations and Prototype Learning},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
volume = {44},
number = {3},
pages = {1181--1193},
doi = {10.1109/tmi.2024.3484166}
}
EUVIMED