mlsanityData to 7 Oct 2026

CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation

arXiv 2211.12081 ↗First posted 22 Nov 2022cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-invariant features is key for achieving Domain Generalization (DG). However, existing DG methods can hardly achieve effective disentanglement to get high generalizability. To deal with this problem, we propose an efficient Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for generalizable medical image segmentation. First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code, where the former is sent to a segmentation model that is not affected by the domain shift, and the disentangle network is regularized by a decoder that combines the anatomical and style codes to reconstruct the input image. Second, to achieve better disentanglement, a contrastive loss is proposed to encourage the style codes from the same domain and different domains to be compact and divergent, respectively. Thirdly, to further improve generalizability, we propose a style augmentation method based on the disentanglement representation to synthesize images in various unseen styles with shared anatomical structures. Our method was validated on a public multi-site fundus image dataset for optic cup and disc segmentation and an in-house multi-site Nasopharyngeal Carcinoma Magnetic Resonance Image (NPC-MRI) dataset for nasopharynx Gross Tumor Volume (GTVnx) segmentation. Experimental results showed that the proposed CDDSA achieved remarkable generalizability across different domains, and it outperformed several state-of-the-art methods in domain-generalizable segmentation.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 36 of its 57 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

36 of 57 references.

References · 36

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  9. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  11. 2013Domain Generalization via Invariant Feature Representationcited by 622
  12. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
24 more
  1. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  2. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  3. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  4. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  5. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  6. 2019REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographscited by 226
  7. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  8. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  9. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  10. 2020CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentationcited by 79
  11. 2020DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasetscited by 70
  12. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  13. 2019Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentationcited by 50
  14. 2021Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentationcited by 49
  15. 2021Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentationcited by 33
  16. 2021Domain and Content Adaptive Convolution based Multi-Source Domain Generalization for Medical Image Segmentationcited by 29
  17. 2018Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentationcited by 21
  18. 2022Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structurescited by 18
  19. 2020MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraintcited by 17
  20. 2020Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Imagescited by 17
  21. 2021Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentationcited by 16
  22. 2022Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restorationcited by 15
  23. 2021A New Bidirectional Unsupervised Domain Adaptation Segmentation Frameworkcited by 10
  24. 2019Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasoundcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 8; 2026: 3.

18 papers.

Sort:

By area:

  1. 20233DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentationcited by 70
  2. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  3. 2024Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentationcited by 9
  4. 2025Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentationcited by 7
  5. 2024Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinementcited by 5
  6. 2024Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentationcited by 3
  7. 2024A dataset of primary nasopharyngeal carcinoma MRI with multi-modalities segmentationcited by 2
  8. 2023Only Positive Cases: 5-fold High-order Attention Interaction Model for Skin Segmentation Derived Classificationcited by 1
  9. 2025Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentationcited by 1
  10. 2025MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Networkcited by 1
  11. 2025Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Methodcited by 1
  12. 2025Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalizationcited by 1
6 more
  1. 2025Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustnesscited by 1
  2. 2025Casual Inference via Style Bias Deconfounding for Domain Generalizationcited by 0
  3. 2025F^2TTA: Free-Form Test-Time Adaptation on Cross-Domain Medical Image Classification via Image-Level Disentangled Prompt Tuningcited by 0
  4. 2026Contour-Guided Query-Based Feature Fusion for Boundary-Aware and Generalizable Cardiac Ultrasound Segmentationcited by 0
  5. 2026Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screeningcited by 0
  6. 2026Lighting-Aware Representation Learning under Controllable Lighting Variationcited by 0