• Home
  • Search
  • Frequency-aware domain randomization for single-source domain generalization in medical image segmentation.
  • https://doi.org/10.1002/mp.70118Copy DOI Icon

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

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

Medical image segmentation is vital for clinical diagnosis, yet deep learning models face domain shift challenges when test data distributions differ from training data. Single-source domain generalization (DG) has emerged as a solution to these limitations of deep learning models by training models on a single source domain to generalize to unseen target domains. Current single-source DG methods employ domain randomization (e.g., input/feature-space perturbations) to simulate unseen target domains, but face two key limitations: (1) Texture bias in CNN-based architectures due to their local processing nature, leading to overfitting and poor generalization; (2) Restricted augmented style diversity caused by solely source-dependent feature perturbations and input- or feature-only augmentation, resulting in insufficient coverage of target domain distributions and degraded model's generalizationability. Motivated by the Fourier transform's capability to model global dependency and decouple domain invariant features, we propose Random Domain Generalization (RandDG), a frequency-aware domain randomization method for single-source DG in medical image segmentation. This method enhances generalization ability through coordinated input and feature spaces perturbations while maintaining parameter efficiency via lightweight architectural design in the frequencydomain. The proposed RandDG incorporates a novel Global U-Shape Network (GUNet) segmentation architecture for efficient long-range dependency modeling and a Uniform Low Frequency spectrum Transform (ULoFT) filter for feature-space perturbation to enhance domain generalization ability, facilitating the learning of global domain invariant structural information through consistency constraints within the dual-space randomization framework. More specifically, first, the GUNet architecture combines a lightweight encoder with frequency-domain global filtering and forms a U-shape structure through a skip-connected decoder, utilizing Fourier transforms to capture long-range dependencies while minimizing parameters. Second, the ULoFT filter perturbs feature-space styles by Bernoulli mixing statistics of the source low-frequency amplitude spectrum with uniformly sampled values, thereby reducing sole reliance on source statistics and broadening the coverage of potential target domains. Third, a dual-space randomization framework simultaneously applies input-space style augmentation via global intensity nonlinear augmentation (GIN) filters and feature-space amplitude spectrum perturbation via ULoFT filter, regularized by a consistency loss to enforce domain invariant representationlearning. Experiments were conducted on an abdominal CT-MRI dataset for abdominal multi-organ segmentation from CT to T2 spectral presaturation with inversion recovery (T2-SPIR) MRI and a cross-center prostate dataset for prostate segmentation from one center to others. The proposed RandDG method demonstrated superior generalization ability, significantly improving robustness against domain shifts compared to competitive methods. When tested on unseen domains, the proposed method achieved an average DSC of 87.96% and an average HD of 4.82 mm on the abdominal CT-MRI dataset, as well as an average DSC of 75.95% and an average HD of 8.36 mm on the cross-center prostate dataset. Compared to the UNet baseline, the proposed method achieved an improvement of 10.65% in average DSC and a reduction of 5.23 mm in average HD on the abdominal CT-MRI dataset, as well as 19.36% higher average DSC and 3.39 mm lower average HD on the cross-center prostate dataset. Ablation studies confirmed the effectiveness of each component of the proposed RandDGmethod. The proposed RandDG method effectively addresses the critical challenges of texture bias and limited style diversity in single-source DG for medical image segmentation through frequency-aware dual-space randomization framework. This method shows promise for practical deployment in clinical settings, where target domain data may not always beavailable.

Similar Papers
  • 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
  • Citations13

Domain-Aware Dual Attention for Generalized Medical Image Segmentation on Unseen Domains.

  • May 01, 2023
  • IEEE Journal of Biomedical and Health Informatics
  • Huilin Lai +4
  • Conference Article
  • Citations61

Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing

  • Oct 10, 2022
  • Qianyu Zhou +5
  • Research Article
  • Citations7

Adaptive Domain Generalization Via Online Disagreement Minimization.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Xin Zhang +1
  • Research Article
  • Citations22

Dynamic domain generalization for medical image segmentation.

  • Apr 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Zhiming Cheng +3
  • Research Article
  • Citations24

Style and content separation network for remote sensing image cross-scene generalization

  • May 22, 2023
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Sihan Zhu +3
  • Research Article
  • Citations4

Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection

  • Jan 01, 2026
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hao Li +8
  • 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
  • Research Article
  • Citations1

GaitDG: A Single-Source Domain Generalization Framework for Cross-Domain Gait Recognition

  • Jan 01, 2025
  • IEEE Transactions on Information Forensics and Security
  • Guancheng Lin +6
  • Research Article
  • Citations42

Single-Domain Generalization in Medical Image Segmentation via Test-Time Adaptation from Shape Dictionary

  • Jun 28, 2022
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Quande Liu +3
  • Conference Article
  • Citations1

Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption

  • Aug 21, 2022
  • Ahmed Frikha +2
  • Research Article
  • Citations7

UniAda: Domain Unifying and Adapting Network for Generalizable Medical Image Segmentation.

  • May 01, 2025
  • IEEE transactions on medical imaging
  • Zhongzhou Zhang +7
  • Conference Article
  • Citations11

Learning Transferrable and Interpretable Representations for Domain Generalization

  • Oct 17, 2021
  • Zhekai Du +4
  • Book Chapter
  • Citations51

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

  • Jan 01, 2022
  • Boqiang Xu +3
  • Research Article
  • Citations5

Domain-Generalized Discrete Diffusion Model for Cross-Domain Medical Image Segmentation.

  • Nov 01, 2025
  • IEEE transactions on medical imaging
  • Heran Yang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.