Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation
IEEE Transactions on Medical Imaging · 2025-09 · 44 (9) · 3741-3755
DOI: 10.1109/tmi.2025.3564765 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-09. Verfasst von Zihan Cheng und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: NSFC Project, China Postdoctoral Science Foundation, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model's generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model's learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. The code is available at https://github.com/orange-czh/Mamba-Sea.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- NSFC Project
- China Postdoctoral Science Foundation
- Fundamental Research Funds for the Central Universities
- State Key Laboratory Fund
- Postdoctoral Fellowship Program of CPSF
- Jiangsu Funding Program for Excellent Postdoctoral Talent
- Jiangsu Science and Technology Major Project
Zitieren
APA
Cheng, Z., Guo, J., Zhang, J., Qi, L., Zhou, L., Shi, Y., & Gao, Y. (2025). Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation. IEEE Transactions on Medical Imaging, 44(9), 3741-3755. https://doi.org/10.1109/tmi.2025.3564765
Vancouver
Cheng Z, Guo J, Zhang J, Qi L, Zhou L, Shi Y, et al. Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation. IEEE Transactions on Medical Imaging. 2025;44(9):3741-3755. doi:10.1109/tmi.2025.3564765
BibTeX
@article{Cheng2025,
author = {Cheng, Zihan and Guo, Jintao and Zhang, Jian and Qi, Lei and Zhou, Luping and Shi, Yinghuan and Gao, Yang},
title = {Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
volume = {44},
number = {9},
pages = {3741--3755},
doi = {10.1109/tmi.2025.3564765}
}
EUVIMED