• Home
  • Search
  • Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation.
  • Cite Icon19
  • https://doi.org/10.1109/tmi.2025.3564765Copy DOI Icon

Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • Research Article

Frequency-aware domain randomization for single-source domain generalization in medical image segmentation.

  • Nov 29, 2025
  • Medical physics
  • Jiayi Wu +6
  • PDF
  • Research Article

Infproto-Powered Adaptive Classifier and Agnostic Feature Learning for Single Domain Generalization in Medical Images

  • Jul 08, 2024
  • International Journal of Computer Vision
  • Xiaoqing Guo +2
  • Research Article
  • Citations2

Adaptive wavelet‐VNet for single‐sample test time adaptation in medical image segmentation

  • Oct 01, 2024
  • Medical Physics
  • Xiaoxue Qian +2
  • Research Article
  • Citations224

Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation.

  • Apr 01, 2023
  • IEEE Transactions on Medical Imaging
  • Cheng Ouyang +6
  • Research Article
  • Citations1

Domain composition and attention network trained with synthesized unlabeled images for generalizable medical image segmentation

  • Jun 28, 2024
  • Neurocomputing
  • Jiangshan Lu +6
  • Book Chapter
  • Citations7

Self-supervised Test-Time Adaptation for Medical Image Segmentation

  • Jan 01, 2022
  • Hao Li +12
  • Book Chapter

FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentation

  • Oct 21, 2025
  • Frontiers in artificial intelligence and applications
  • Yucheng Song +4
  • Research Article

Vision Mamba Empowered by Dynamic Domain Generalization for Cross-Modality Medical Segmentation.

  • Oct 16, 2025
  • Journal of imaging informatics in medicine
  • Yan Shi +4
  • Research Article
  • Citations30

S-CUDA: Self-cleansing unsupervised domain adaptation for medical image segmentation.

  • Dec 01, 2021
  • Medical Image Analysis
  • Luyan Liu +4
  • Book Chapter
  • Citations49

Semi-supervised Meta-learning with Disentanglement for Domain-Generalised Medical Image Segmentation

  • Jan 01, 2021
  • Xiao Liu +3
  • Research Article
  • Citations2

Diverse Target and Contribution Scheduling for Domain Generalization.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Shaocong Long +4
  • Research Article
  • Citations29

Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization

  • Aug 18, 2022
  • Pattern Recognition
  • Ruiqi Wang +3
  • Research Article
  • Citations1

Prototype bank-driven test-time adaptation for medical ultrasound image segmentation.

  • Jan 01, 2026
  • Medical physics
  • Wenhan Wang +5
  • Research Article
  • Citations7

Adaptive Domain Generalization Via Online Disagreement Minimization.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Xin Zhang +1
  • Dissertation
  • Citations1

Domain adaptation and generalization for visual recognition

  • Jan 01, 2017
  • Li Niu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.