Authors : Sony Annem

Volume/Issue : Volume 10 - 2025, Issue 5 - May

---

Google Scholar : https://tinyurl.com/544sx7wd

DOI : https://doi.org/10.38124/ijisrt/25may829

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Diffusion models have recently shown great success in creating high-quality images. In this study, we test how well these models work on different types of MRI scans, including brain images, chromatin cell structures, lung, spine and heart MRIs. Instead of using a single model for all types, we experiment with each MRI type separately to see how well diffusion models can handle the unique features of each one. Our early results show that diffusion models can learn the important details in each kind of scan, but the quality of the results can vary depending on the image type. This ongoing work helps us understand the strengths and limits of generative models in medical imaging.

References :

1. Choi, S., Lee, H., & Paik, M. C. (2023). MRI super-resolution using conditional diffusion probabilistic models. IEEE Transactions on Medical Imaging, 42(4), 871–882.
2. Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840–6851. https://arxiv.org/abs/2006.11239
3. Song, Y., & Ermon, S. (2020). Score-based generative modeling through stochastic differential equations. International Conference on Learning Representations (ICLR). https://arxiv.org/abs/2011.13456
4. Dhariwal, P., & Nichol, A. (2021). Diffusion models beat GANs on image synthesis. Advances in Neural Information Processing Systems, 34, 8780–8794. https://arxiv.org/abs/2105.05233
5. Wolleb, J., Sandkühler, P., Karimi, D., & Cattin, P. C. (2021). Diffusion models for medical image analysis. arXiv preprint. https://arxiv.org/abs/2111.07891
6. Pinaya, W. H. L., Mechelli, A., & Sato, J. R. (2022). Brain imaging generation with latent diffusion models. Medical Image Analysis, 82, 102605. https://arxiv.org/abs/2209.07162
7. Choi, S., Lee, H., & Paik, M. C. (2023). MRI super-resolution using conditional diffusion probabilistic models. IEEE Transactions on Medical Imaging, 42(4), 871–882.
8. Lyu, Q., Zhang, K., Fu, Y., et al. (2023). 4D diffusion models for dynamic MRI reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14698–14708.
9. Dorjsembe, B., & Park, B. (2022). Generating realistic brain MR images using diffusion models. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). https://arxiv.org/abs/2209.15199
10. Wolleb, J., Sandkühler, P., & Cattin, P. C. (2023). Diffusion models for medical image segmentation. Medical Image Analysis, 85, 102732. https://arxiv.org/abs/2208.02973
11. Zhou, Z., Wang, J., & Bai, J. (2022). Latent diffusion models for 3D medical image generation. arXiv preprint. https://arxiv.org/abs/2211.13867
12. Mittal, R., Mewada, R., & Sharma, M. (2023). Denoising diffusion models for multi-modal medical image synthesis. Neurocomputing, 532, 119804.
13. Luo, Y., Chen, M., Zhang, Y., et al. (2022). Multi-conditional diffusion model for medical image synthesis. IEEE Transactions on Medical Imaging. https://arxiv.org/abs/2211.01734
14. Ternes, L., Schneider, M., Möller, H. E., & Teschendorff, A. E. (2022). Image denoising and reconstruction in MRI using denoising diffusion models. Magnetic Resonance Imaging, 90, 27–39.
15. Haque, A., Bi, J., & Khan, A. (2022). Brain MRI tumor segmentation using diffusion-based image generation. Biomedical Signal Processing and Control, 78, 103920.
16. Tzeng, E., Yang, J., & Sun, W. (2022). Diffusion models for MR image enhancement and reconstruction. Computerized Medical Imaging and Graphics, 97, 102066.
17. Yu, L., Wang, S., Li, C., et al. (2022). A latent diffusion approach for PET-to-MRI synthesis. IEEE Journal of Biomedical and Health Informatics, 26(7), 3314–3323.
18. Schilling, K. G., et al. (2021). Diffusion models for tractography in diffusion MRI: Principles and challenges. NeuroImage, 245, 118702.
19. Todorov, M. I., Müller, S., & Schifferer, M. (2022). Revolutionizing medical imaging with denoising diffusion models. Nature Machine Intelligence, 4, 843–853.
20. Han, J., Zhang, C., Huang, Y., et al. (2023). DDPM-MedSeg: Diffusion-based medical image segmentation. arXiv preprint. https://arxiv.org/abs/2302.05420
21. Bouchacourt, D., Lee, Y., & Alahi, A. (2022). Masked conditional diffusion models for medical image inpainting. MICCAI Workshops. https://arxiv.org/abs/2210.00939
22. Lyu, Q., Zhang, K., Fu, Y., et al. (2023). 4D diffusion models for dynamic MRI reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14698–14708.
23. Dorjsembe, B., & Park, B. (2022). Generating realistic brain MR images using diffusion models. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). https://arxiv.org/abs/2209.15199
24. Wolleb, J., Sandkühler, P., & Cattin, P. C. (2023). Diffusion models for medical image segmentation. Medical Image Analysis, 85, 102732. https://arxiv.org/abs/2208.02973
25. Zhou, Z., Wang, J., & Bai, J. (2022). Latent diffusion models for 3D medical image generation. arXiv preprint. https://arxiv.org/abs/2211.13867
26. Mittal, R., Mewada, R., & Sharma, M. (2023). Denoising diffusion models for multi-modal medical image synthesis. Neurocomputing, 532, 119804.
27. Luo, Y., Chen, M., Zhang, Y., et al. (2022). Multi-conditional diffusion model for medical image synthesis. IEEE Transactions on Medical Imaging. https://arxiv.org/abs/2211.01734
28. Ternes, L., Schneider, M., Möller, H. E., & Teschendorff, A. E. (2022). Image denoising and reconstruction in MRI using denoising diffusion models. Magnetic Resonance Imaging, 90, 27–39.
29. Haque, A., Bi, J., & Khan, A. (2022). Brain MRI tumor segmentation using diffusion-based image generation. Biomedical Signal Processing and Control, 78, 103920.
30. Tzeng, E., Yang, J., & Sun, W. (2022). Diffusion models for MR image enhancement and reconstruction. Computerized Medical Imaging and Graphics, 97, 102066.
31. Yu, L., Wang, S., Li, C., et al. (2022). A latent diffusion approach for PET-to-MRI synthesis. IEEE Journal of Biomedical and Health Informatics, 26(7), 3314–3323.
32. Schilling, K. G., et al. (2021). Diffusion models for tractography in diffusion MRI: Principles and challenges. NeuroImage, 245, 118702.
33. Todorov, M. I., Müller, S., & Schifferer, M. (2022). Revolutionizing medical imaging with denoising diffusion models. Nature Machine Intelligence, 4, 843–853.
34. Han, J., Zhang, C., Huang, Y., et al. (2023). DDPM-MedSeg: Diffusion-based medical image segmentation. arXiv preprint. https://arxiv.org/abs/2302.05420
35. Bouchacourt, D., Lee, Y., & Alahi, A. (2022). Masked conditional diffusion models for medical image inpainting. MICCAI Workshops. https://arxiv.org/abs/2210.00939
36. Lin, Z., Wang, Z., Yu, L., et al. (2023). Reconstruction of undersampled MRI using score- based diffusion models. Medical Image Analysis, 88, 102848.
37. Wang, Y., He, Y., Yang, D., et al. (2023). Diffusion model for unsupervised anomaly detection in MRI. Computer Methods and Programs in Biomedicine, 234, 107454.
38. Wu, X., Qiu, H., & Li, H. (2023). Conditional DDPM for low-dose MRI reconstruction. IEEE Access, 11, 20433–20443.
39. Zhu, C., & Li, X. (2023). DDPM-based joint super-resolution and denoising of multi- sequence MRI. Neural Computing and Applications, 35, 12759–12774.
40. Fan, Y., Liao, H., Huang, S., Luo, Y., Fu, H., & Qi, H. (2023). A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI. arXiv preprint arXiv:2311.11383. https://arxiv.org/abs/2311.11383
41. Jiang, Y., Wang, Y., & Zhang, X. (2023). Diffusion Models in Medical Imaging: A Comprehensive Survey.        Medical Image   Analysis, 85, 102732.
42. https://www.sciencedirect.com/science/article/abs/pii/S1361841523001068
43. Xiang, T., Yurt, M., Syed, A. B., Setsompop, K., & Chaudhari, A. (2023). DDM²: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models. arXiv preprint arXiv:2302.03018. https://arxiv.org/abs/2302.03018
44. Khader, F., Mueller-Franzes, G., Arasteh, S. T., Han, T., Haarburger, C., Schulze-Hagen, M., ... & Truhn, D. (2022). Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation. arXiv preprint arXiv:2211.03364. https://arxiv.org/abs/2211.03364
45. Dorjsembe, Z., Pao, H. K., Odonchimed, S., & Xiao, F. (2023). Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis. arXiv preprint arXiv:2305.18453. https://arxiv.org/abs/2305.18453
46. Wolleb, J., Sandkühler, P., Karimi, D., & Cattin, P. C. (2021). Diffusion Models for Medical Image Analysis. arXiv preprint arXiv:2111.07891. https://arxiv.org/abs/2111.07891
47. Todorov, M. I., Müller, S., & Schifferer, M. (2022). Revolutionizing Medical Imaging with Denoising Diffusion Models. Nature Machine Intelligence, 4, 843–853.
48. Lyu, Q., Zhang, K., Fu, Y., et al. (2023). 4D Diffusion Models for Dynamic MRI Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14698–14708.
49. Choi, S., Lee, H., & Paik, M. C. (2023). MRI Super-Resolution Using Conditional Diffusion Probabilistic Models. IEEE Transactions on Medical Imaging, 42(4), 871–882.
50. Pinaya, W. H. L., Mechelli, A., & Sato, J. R. (2022). Brain Imaging Generation with Latent Diffusion Models. Medical Image Analysis, 82, 102605.
51. Zhou, Z., Wang, J., & Bai, J. (2022). Latent Diffusion Models for 3D Medical Image Generation. arXiv preprint arXiv:2211.13867. https://arxiv.org/abs/2211.13867
52. Mittal, R., Mewada, R., & Sharma, M. (2023). Denoising Diffusion Models for Multi-Modal Medical Image Synthesis. Neurocomputing, 532, 119804.
53. Luo, Y., Chen, M., Zhang, Y., et al. (2022). Multi-Conditional Diffusion Model for Medical Image Synthesis. IEEE Transactions on Medical Imaging. https://arxiv.org/abs/2211.01734.
54. Ternes, L., Schneider, M., Möller, H. E., & Teschendorff, A. E. (2022). Image Denoising and Reconstruction in MRI Using Denoising Diffusion Models. Magnetic Resonance Imaging, 90, 27–39.
55. Haque, A., Bi, J., & Khan, A. (2022). Brain MRI Tumor Segmentation Using Diffusion-Based Image Generation. Biomedical Signal Processing and Control, 78, 103920.
56. Tzeng, E., Yang, J., & Sun, W. (2022). Diffusion Models for MR Image Enhancement and Reconstruction. Computerized Medical Imaging and Graphics, 97, 102066.
57. Yu, L., Wang, S., Li, C., et al. (2022). A Latent Diffusion Approach for PET-to-MRI Synthesis. IEEE Journal of Biomedical and Health Informatics, 26(7), 3314–3323.
58. Schilling, K. G., et al. (2021). Diffusion Models for Tractography in Diffusion MRI: Principles and Challenges. NeuroImage, 245, 118702.
59. Han, J., Zhang, C., Huang, Y., et al. (2023). DDPM-MedSeg: Diffusion-Based Medical Image Segmentation. arXiv preprint arXiv:2302.05420. https://arxiv.org/abs/2302.05420
60. Bouchacourt, D., Lee, Y., & Alahi, A. (2022). Masked Conditional Diffusion Models for Medical Image Inpainting. MICCAI Workshops. https://arxiv.org/abs/2210.00939