• Home
  • Search
  • Collaborative Learning of Augmentation and Disentanglement for Semi-Supervised Domain Generalized Medical Image Segmentation.
  • Cite Icon1
  • https://doi.org/10.1109/tmi.2025.3596247Copy DOI Icon

Collaborative Learning of Augmentation and Disentanglement for Semi-Supervised Domain Generalized Medical Image Segmentation.

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

This paper explores a challenging yet realistic scenario: semi-supervised domain generalization (SSDG) that includes label scarcity and domain shift problems. We pinpoint that the limitations of previous SSDG methods lie in 1) neglecting the difference between domain shifts existing within a training dataset (intra-domain shift, IDS) and those occurring between training and testing datasets (cross-domain shift, CDS) and 2) overlooking the interplay between label scarcity and domain shifts, resulting in these methods merely stitching together semi-supervised learning (SSL) and domain generalization (DG) techniques. Considering these limitations, we propose a novel perspective to decompose SSDG into the combination of unsupervised domain adaptation (UDA) and DG problems. To this end, we design a causal augmentation and disentanglement framework (CausalAD) for semi-supervised domain generalized medical image segmentation. Concretely, CausalAD involves two collaborative processes: an augmentation process, which utilizes disentangled style factors to perform style augmentation for UDA, and a disentanglement process, which decouples domain-invariant (content) and domain-variant (noise and style) features for DG. Furthermore, we propose a proxy-based self-paced training strategy (ProSPT) to guide the training of CausalAD by gradually selecting unlabeled image pixels with high-quality pseudo labels in a self-paced training manner. Finally, we introduce a hierarchical structural causal model (HSCM) to explain the intuition and concept behind our method. Extensive experiments in the cross-sequence, cross-site, and cross-modality semi-supervised domain generalized medical image segmentation settings show the effectiveness of CausalAD and its superiority over the state-of-the-art. The code is available at https://github.com/Senyh/CausalAD.

Similar Papers
  • Single Report
  • Citations2

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

  • Dec 28, 2021
  • Philip Hart +7
  • Conference Article
  • Citations14

Semi-supervised Domain Adaptation in Graph Transfer Learning

  • Aug 01, 2023
  • Ziyue Qiao +5
  • Research Article
  • Citations147

Towards better benchmarking using the CWRU bearing fault dataset

  • Dec 30, 2021
  • Mechanical Systems and Signal Processing
  • Jacob Hendriks +2
  • Conference Article
  • Citations7

MCKD: Mutually Collaborative Knowledge Distillation For Federated Domain Adaptation And Generalization

  • Jun 04, 2023
  • Ziwei Niu +5
  • Research Article
  • Citations5

Method for Automatic Selection of Parameters in Normal Tissue Complication Probability Modeling

  • Mar 06, 2018
  • International Journal of Radiation Oncology*Biology*Physics
  • Damianos Christophides +4
  • PDF
  • Research Article
  • Citations93

Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine

  • Feb 17, 2022
  • Scientific reports
  • Lin Lawrence Guo +7
  • Research Article
  • Citations3

Unpaired Image Translation to Mitigate Domain Shift in Liquid Argon Time Projection Chamber Detector Responses

  • Oct 08, 2024
  • Machine Learning: Science and Technology
  • Yi Huang +6
  • Research Article
  • Citations3

High-frequency-based multi-spectral attention for domain generalization

  • May 14, 2025
  • Artificial Intelligence Review
  • Surong Ying +2
  • Book Chapter
  • Citations25

Self Domain Adapted Network

  • Jan 01, 2020
  • Yufan He +4
  • Conference Article
  • Citations77

Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow

  • Jun 01, 2015
  • Rui Caseiro +3
  • Research Article
  • Citations31

Domain Generalization in Computational Pathology: Survey and Guidelines

  • Jun 14, 2025
  • ACM Computing Surveys
  • Mostafa Jahanifar +10
  • Research Article
  • Citations4

Predicting the need for a replan in oropharyngeal cancer: A radiomic, clinical, and dosimetric model.

  • Dec 15, 2023
  • Medical physics
  • Tricia A Chinnery +3
  • Research Article

Fairness across domains: a unified fairness-aware framework for domain generalization and unsupervised adaptation

  • Jan 01, 2026
  • Frontiers in Big Data
  • Kai Jiang +6
  • Research Article
  • Citations81

LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation.

  • Mar 01, 2023
  • IEEE Transactions on Medical Imaging
  • Ziyuan Zhao +5
  • Research Article
  • Citations12

EDRL: Entropy-guided disentangled representation learning for unsupervised domain adaptation in semantic segmentation

  • Jul 25, 2023
  • Computer Methods and Programs in Biomedicine
  • Runze Wang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.