Optimal Transport and Central Moment Consistency Regularization for Semi-Supervised Medical Image Segmentation
IEEE Transactions on Medical Imaging · 2025-08 · 44 (8) · 3397-3409
DOI: 10.1109/tmi.2025.3563500 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-08. Verfasst von Xiuzhen Guo und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Supervised Machine Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Outstanding Young Scientist Program, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Semi-supervised learning leverages insights from unlabeled data to enhance generalizability of the model, thereby decreasing the dependence on extensive labeled datasets. Most existing methods overly focus on local representations while neglecting the learning of global structures. On the one hand, given that labeled and unlabeled images are presumed to originate from the same distribution, it is probable that similar regional features observed in both types of images correspond to the same label. Current label propagation techniques, which predominantly propagate label information through the construction of graph structures or similarity matrices, heavily depend on localized information and are prone to converge to local optima. In contrast, optimal transport considers the entire distribution. This facilitates more comprehensive and efficient label propagation. On the other hand, current consistency regularization-based methods focus on the local view, we believe learning from a global geometric view may capture more information. Geometric moment information of the sample itself can constrain the overall geometric structure. Inspired by these observations, this paper introduces a semi-supervised medical image segmentation framework that integrates optimal transport and central moment consistency regularization (OTCMC) from a global perspective. Firstly, we pass label information from labeled data to unlabeled data by optimal transport. Secondly, we incorporate central moment consistency regularization to focus the network on the geometric structure of images. Our method achieves the state-of-the-art (SOTA) performance on a series of datasets, including the NIH pancreas, left atrium, brain tumor, and skin lesion dermoscopy datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Beijing Outstanding Young Scientist Program
- Beijing Natural Science Foundation
Zitieren
APA
Guo, X., Yu, L., Shi, J., Wang, H., Zhao, J., Zhang, R., Li, H., & Lei, N. (2025). Optimal Transport and Central Moment Consistency Regularization for Semi-Supervised Medical Image Segmentation. IEEE Transactions on Medical Imaging, 44(8), 3397-3409. https://doi.org/10.1109/tmi.2025.3563500
Vancouver
Guo X, Yu L, Shi J, Wang H, Zhao J, Zhang R, et al. Optimal Transport and Central Moment Consistency Regularization for Semi-Supervised Medical Image Segmentation. IEEE Transactions on Medical Imaging. 2025;44(8):3397-3409. doi:10.1109/tmi.2025.3563500
BibTeX
@article{Guo2025,
author = {Guo, Xiuzhen and Yu, Lianyuan and Shi, Ji and Wang, Hongxiao and Zhao, Jiangyuan and Zhang, Rongguo and Li, Hongwei and Lei, Na},
title = {Optimal Transport and Central Moment Consistency Regularization for Semi-Supervised Medical Image Segmentation},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
volume = {44},
number = {8},
pages = {3397--3409},
doi = {10.1109/tmi.2025.3563500}
}
EUVIMED