mlsanityData to 14 Oct 2026

Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?

arXiv 2508.06327 ↗First posted 8 Aug 2025cs.CVcited by 2

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Magnetic resonance (MR) imaging, including cardiac MR, is prone to domain shift due to variations in imaging devices and acquisition protocols. This challenge limits the deployment of trained AI models in real-world scenarios, where performance degrades on unseen domains. Traditional solutions involve increasing the size of the dataset through ad-hoc image augmentation or additional online training/transfer learning, which have several limitations. Synthetic data offers a promising alternative, but anatomical/structural consistency constraints limit the effectiveness of generative models in creating image-label pairs. To address this, we propose a diffusion model (DM) trained on a source domain that generates synthetic cardiac MR images that resemble a given reference. The synthetic data maintains spatial and structural fidelity, ensuring similarity to the source domain and compatibility with the segmentation mask. We assess the utility of our generative approach in multi-centre cardiac MR segmentation, using the 2D nnU-Net, 3D nnU-Net and vanilla U-Net segmentation networks. We explore domain generalisation, where, domain-invariant segmentation models are trained on synthetic source domain data, and domain adaptation, where, we shift target domain data towards the source domain using the DM. Both strategies significantly improved segmentation performance on data from an unseen target domain, in terms of surface-based metrics (Welch's t-test, p < 0.01), compared to training segmentation models on real data alone. The proposed method ameliorates the need for transfer learning or online training to address domain shift challenges in cardiac MR image analysis, especially useful in data-scarce settings.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 23 of its 37 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

23 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models28 Mar
  2. 2023Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models5 Jun
  3. 2023Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images12 May

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  4. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  5. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 635
  6. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  7. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
  8. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 240
  9. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  10. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  11. 2019Deep learning for cardiac image segmentation: A reviewcited by 131
  12. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
8 more
  1. 2022Towards a Guideline for Evaluation Metrics in Medical Image Segmentationcited by 60
  2. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 48
  3. 2020Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRIcited by 28
  4. 2021Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentationcited by 28
  5. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 28
  6. 2021Controllable cardiac synthesis via disentangled anatomy arithmeticcited by 9
  7. 2024Enhancing Sample Generation of Diffusion Models using Noise Level Correctioncited by 4
  8. 2021The Impact of Domain Shift on Left and Right Ventricle Segmentation in Short Axis Cardiac MR Imagescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Studycited by 0
  2. 2026Synthetic Cardiac MRI Image Generation using Deep Generative Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
  2. 2024Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles
  3. 2026CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis
  4. 2025Reverse Imaging for Wide-spectrum Generalization of Cardiac MRI Segmentation
  5. 2024A Domain Translation Framework with an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Images
  6. 2025Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI
  7. 2023Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation
  8. 2025Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction