mlsanityData to 14 Oct 2026

Cycle Diffusion Model for Counterfactual Image Generation

arXiv 2509.24267 ↗First posted 29 Sep 2025cs.CV cs.AIcited by 1

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Deep generative models have demonstrated remarkable success in medical image synthesis. However, ensuring conditioning faithfulness and high-quality synthetic images for direct or counterfactual generation remains a challenge. In this work, we introduce a cycle training framework to fine-tune diffusion models for improved conditioning adherence and enhanced synthetic image realism. Our approach, Cycle Diffusion Model (CDM), enforces consistency between generated and original images by incorporating cycle constraints, enabling more reliable direct and counterfactual generation. Experiments on a combined 3D brain MRI dataset (from ABCD, HCP aging & young adults, ADNI, and PPMI) show that our method improves conditioning accuracy and enhances image quality as measured by FID and SSIM. The results suggest that the cycle strategy used in CDM can be an effective method for refining diffusion-based medical image generation, with applications in data augmentation, counterfactual, and disease progression modeling.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 20 of its 38 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

20 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 20253D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces18 Feb
  2. 2024MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRI21 Jul
  3. 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge6 May
  4. 2022Brain Imaging Generation with Latent Diffusion Models15 Sep

Other references · 16

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2017Neural Discrete Representation Learningcited by 4,712
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  7. 2019Med3D: Transfer Learning for 3D Medical Image Analysiscited by 288
  8. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  9. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  10. 2019Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networkscited by 65
  11. 2023MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Imagescited by 41
  12. 2023CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulationcited by 41
4 more
  1. 2021Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative modelscited by 36
  2. 2022Morphology-preserving Autoregressive 3D Generative Modelling of the Braincited by 15
  3. 2023Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIscited by 12
  4. 2024Latent Causal Modeling for 3D Brain MRI Counterfactualscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Anatomically Guided Latent Diffusion for Brain MRI Progression Modelingcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis
  2. 2025Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance
  3. 2024Promptable Counterfactual Diffusion Model for Unified Brain Tumor Segmentation and Generation with MRIs
  4. 2024Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models
  5. 2026MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation
  6. 2022Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
  7. 2024Cross-conditioned Diffusion Model for Medical Image to Image Translation
  8. 2023BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys