1. Home
  2. To appear
  3. SynthModDiff: A Diffusion-Based Framewor ...

Informatica


SynthModDiff: A Diffusion-Based Framework for Robust Multi-Domain MRI Synthesis
Pub. online: 13 March 2026      Type: Research Article      Open accessOpen Access
Received
1 March 2025
Accepted
1 March 2026
Published
13 March 2026

Abstract

Magnetic Resonance Imaging (MRI) is crucial for clinical diagnostics, offering high-resolution anatomical and functional imaging without ionizing radiation. However, prolonged acquisition times in conventional MRI lead to motion artifacts, limiting efficiency and reliability. While deep learning models such as GANs and DDPMs show promise in MRI synthesis, DDPMs suffer from stochastic variability that affects image consistency. This study proposes Synthetic Modality Diffusion (SynthModDiff), a novel multi-domain image-to-image translation framework featuring a two-stage diffusion process with a noise-aware Forward Process and Reverse Process to enhance fidelity and reduce residual noise. Experiments across multiple datasets demonstrate state-of-the-art performance in NMAE, SSIM, and PSNR metrics, while preserving fine anatomical details, making SynthModDiff highly suitable for clinical applications like radiotherapy planning.

References

 
Ali, H., Biswas, M.R., Mohsen, F., Shah, U., Alamgir, A., Mousa, O., Shah, Z. (2022). The role of generative adversarial networks in brain MRI: a scoping review. Insights Imaging, 13(1), 98.
 
Berthelon, X., Chenegros, G., Finateu, T., Ieng, S.-H., Benosman, R. (2018). Effects of cooling on the SNR and contrast detection of a low-light event-based camera. IEEE Transactions on Biomedical Circuits and Systems, 12(6), 1467–1474.
 
Bodduna, K., Weickert, J. (2019). Poisson noise removal using multi-frame 3D block matching. In: 2019 8th European Workshop on Visual Information Processing (EUVIP). IEEE, pp. 58–63.
 
Chang, C.-W., Dinh, N.T. (2019). Classification of machine learning frameworks for data-driven thermal fluid models. International Journal of Thermal Sciences, 135, 559–579.
 
Chang, C.-W., Marants, R., Gao, Y., Goette, M., Scholey, J.E., Bradley, J.D., Liu, T., Zhou, J., Sudhyadhom, A., Yang, X. (2022). Multimodal imaging-based material mass density estimation for proton therapy using physics-constrained deep learning. arXiv preprint arXiv:2207.13150.
 
Chen, W., Wu, S., Wang, S., Li, Z., Yang, J., Yao, H., Song, X. (2023). Compound attention and neighbor matching network for multi-contrast MRI super-resolution. arXiv preprint arXiv:2307.02148.
 
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., Choo, J. (2018). StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789–8797.
 
Dayarathna, S., Peiris, H., Islam, K.T., Wong, T.-T., Chen, Z. (2025a). D2Diff: a dual-domain diffusion model for accurate multi-contrast MRI synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, pp. 131–141.
 
Dayarathna, S., Wu, Y., Cai, J., Wong, T.-T., Law, M., Islam, K.T., Peiris, H., Chen, Z. (2025b). MU-Diff: a mutual learning diffusion model for synthetic MRI with Application for brain lesions. npj Artificial Intelligence, 1, 11.
 
Dhariwal, P., Nichol, A. (2021). Diffusion models beat GANs on image synthesis. Advances in Neural Information Processing Systems, 34, 8780–8794.
 
Diakogiannis, F.I., Waldner, F., Caccetta, P., Wu, C. (2020). ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing, 162, 94–114.
 
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139–144.
 
Goudschaal, K., Beeksma, F., Boon, M., Bijveld, M., Visser, J., Hinnen, K., van Kesteren, Z. (2021). Accuracy of an MR-only workflow for prostate radiotherapy using semi-automatically burned-in fiducial markers. Radiation Oncology, 16, 1–13.
 
Grigas, O., Maskeliūnas, R., Damaševičius, R. (2023). Improving structural MRI preprocessing with hybrid transformer GANs. Life, 13(9), 1893.
 
Han, L.H.N., Hien, N.L.H., Huy, L.V., Hieu, N.V. (2024). A deep learning model for multi-domain MRI synthesis using generative adversarial networks. Informatica, 35(2), 283–309.
 
Ho, J., Jain, A., Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840–6851.
 
Hu, M., Wang, J., Chang, C.-W., Liu, T., Yang, X. (2023a). End-to-end brain tumor detection using a graph-feature-based classifier. In: Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging, Vol. 12468. SPIE, pp. 322–327.
 
Hu, M., Wang, J., Chang, C.-W, Liu, T., Yang, X. (2023b). Ultrasound breast tumor detection based on vision graph neural network. In: Medical Imaging 2023: Ultrasonic Imaging and Tomography, Vol. 12470. SPIE, pp. 165–170.
 
Hu, M., Wang, J., Wynne, J., Liu, T., Yang, X. (2023c). A vision-GNN framework for retinopathy classification using optical coherence tomography. In: Medical Imaging 2023: Computer-Aided Diagnosis, Vol. 12465. SPIE, pp. 200–206.
 
Hu, X., Shen, R., Luo, D., Tai, Y., Wang, C., Menze, B.H. (2022). AutoGAN-synthesizer: neural architecture search for cross-modality MRI synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, pp. 397–409.
 
Ionescu, B., Müller, H., Villegas, M., Arenas, H., Boato, G., Dang-Nguyen, D.-T., Dicente Cid, Y., Eickhoff, C., Seco de Herrera, A.G., Gurrin, C., et al. (2017). Overview of ImageCLEF 2017: information extraction from images. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction: 8th International Conference of the CLEF Association, CLEF 2017, Dublin, Ireland, September 11–14, 2017, Proceedings 8. Springer, pp. 315–337.
 
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A. (2017). Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134.
 
Jiang, M., Jia, P., Huang, X., Yuan, Z., Ruan, D., Liu, F., Xia, L. (2025). Frequency-aware diffusion model for multi-modal MRI image synthesis. Journal of Imaging, 11(5), 152.
 
Juneja, M., Minhas, J.S., Singla, N., Kaur, R., Jindal, P. (2024). Denoising techniques for cephalometric x-ray images: a comprehensive review. Multimedia Tools and Applications, 83(17), 49953–49991.
 
Kriukova, E., LaRochelle, E., Pfefer, T.J., Kanniyappan, U., Gioux, S., Pogue, B., Ntziachristos, V., Gorpas, D. (2025). Impact of signal-to-noise ratio and contrast definition on the sensitivity assessment and benchmarking of fluorescence molecular imaging systems. Journal of Biomedical Optics, 30(S1), S13703.
 
Li, M., Li, X., Safai, S., Lomax, A.J., Zhang, Y. (2025). Diffusion Schrödinger bridge models for high-quality MR-to-CT synthesis for proton treatment planning. Medical Physics, 52(7), 17898.
 
Li, X., Shang, K., Wang, G., Butala, M.D. (2023a). DDMM-Synth: a denoising diffusion model for cross-modal medical image synthesis with sparse-view measurement embedding. arXiv preprint arXiv:2303.15770.
 
Li, Y., Wang, J., Chang, C.-W., Patel, P., Jani, A., Mao, H., Liu, T., Yang, X. (2023b). Multi-parametric MRI radiomics analysis with ensemble learning for prostate lesion classification. In: Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging, Vol. 12468. SPIE, pp. 49–54.
 
Li, Y., Wang, J., Hu, M., Patel, P., Mao, H., Liu, T., Yang, X. (2023c). Prostate Gleason score prediction via MRI using capsule network. In: Medical Imaging 2023: Computer-Aided Diagnosis, Vol. 12465. SPIE, pp. 514–519.
 
Li, Y., Zhou, B., Wang, J., Pan, S., Jani, A., Liu, T., Patel, P., Yang, X. (2023d). Ultrasound-based dominant intraprostatic lesion classification with swin transformer. In: Medical Imaging 2023: Ultrasonic Imaging and Tomography, Vol. 12470. SPIE, pp. 146–151.
 
Li, Y., Shao, H.-C., Liang, X., Chen, L., Li, R., Jiang, S., Wang, J., Zhang, Y. (2024). Zero-shot medical image translation via frequency-guided diffusion models. IEEE Transactions on Medical Imaging, 43(3), 980–993.
 
Liu, Y., Chen, A., Shi, H., Huang, S., Zheng, W., Liu, Z., Zhang, Q., Yang, X. (2021). CT synthesis from MRI using multi-cycle GAN for head-and-neck radiation therapy. Computerized Medical Imaging and Graphics, 91, 101953.
 
Luo, Y., Toth, D., Jiang, K., Pushparajah, K., Rhode, K. (2020). Ultra-DenseNet for low-dose X-ray image denoising in cardiac catheter-based procedures. In: Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges: 10th International Workshop, STACOM 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Revised Selected Papers 10. Springer, pp. 31–42.
 
Lyu, Q., Wang, G. (2022). Conversion between CT and MRI images using diffusion and score-matching models. arXiv preprint arXiv:2209.12104.
 
Makitalo, M., Foi, A. (2012). Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise. IEEE Transactions on Image Processing, 22(1), 91–103.
 
Matviychuk, Y., Mailhé, B., Chen, X., Wang, Q., Kiraly, A., Strobel, N., Nadar, M. (2016). Learning a multiscale patch-based representation for image denoising in X-ray fluoroscopy. In: 2016 IEEE International Conference on Image Processing (ICIP). IEEE, pp. 2330–2334.
 
Moya-Sáez, E., Peña-Nogales, Ó., de Luis-García, R., Alberola-López, C. (2021). A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data. Computer Methods and Programs in Biomedicine, 210, 106371.
 
Nichol, A.Q., Dhariwal, P. (2021). Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, PMLR, pp. 8162–8171.
 
Özbey, M., Dalmaz, O., Dar, S.U., Bedel, H.A., Özturk, Ş., Güngör, A., Çukur, T. (2023). Unsupervised medical image translation with adversarial diffusion models. IEEE Transactions on Medical Imaging, 42(12), 3524–3539.
 
Pan, S., Flores, J., Lin, C.T., Stayman, J.W., Gang, G.J. (2021). Generative adversarial networks and radiomics supervision for lung lesion synthesis. In: Medical Imaging 2021: Physics of Medical Imaging, Vol. 11595. SPIE, pp. 167–172.
 
Pan, S., Abouei, E., Wynne, J., Chang, C.-W., Wang, T., Qiu, R.L., Li, Y., Peng, J., Roper, J., Patel, P., Yu, D.S., Mao, H., Yang, X. (2024). Synthetic CT generation from MRI using 3D transformer-based denoising diffusion model. Medical Physics, 51(4), 2538–2548.
 
Peng, J., Qiu, R.L., Wynne, J.F., Chang, C.-W., Pan, S., Wang, T., Roper, J., Liu, T., Patel, P.R., Yu, D.S., Yang, X. (2024). CBCT-based synthetic CT image generation using conditional denoising diffusion probabilistic model. Medical Physics, 51(3), 1847–1859.
 
Safari, M., Wang, S., Li, Q., Eidex, Z., Qiu, R.L., Chang, C.-W., Mao, H., Yang, X. (2025). Res-MoCoDiff: residual-guided diffusion models for motion artifact correction in brain MRI. Physics in Medicine & Biology, 70(20), 205022.
 
Sohail, M., Riaz, M.N., Wu, J., Long, C., Li, S. (2019). Unpaired multi-contrast MR image synthesis using generative adversarial networks. In: International Workshop on Simulation and Synthesis in Medical Imaging. Springer, pp. 22–31.
 
Song, J., Meng, C., Ermon, S. (2020). Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502.
 
Sun, L., Hu, X., Liu, Y., Cai, H. (2021). Image features of magnetic resonance imaging under the deep learning algorithm in the diagnosis and nursing of malignant tumors. Contrast Media & Molecular Imaging, 2021(1), 1104611.
 
Tiago, C., Snare, S.R., Šprem, J., McLeod, K. (2023). A domain translation framework with an adversarial denoising diffusion model to generate synthetic datasets of echocardiography images. IEEE Access, 11, 17594–17602.
 
Turajlić, E., Karahodzic, V. (2017). An adaptive scheme for X-ray medical image denoising using artificial neural networks and additive white Gaussian noise level estimation in SVD domain. In: CMBEBIH 2017: Proceedings of the International Conference on Medical and Biological Engineering 2017. Springer, pp. 36–40.
 
Wang, Z., Zhang, L., Wang, L., Zhang, Z. (2024). Soft masked mamba diffusion model for ct to mri conversion. arXiv preprint arXiv:2406.15910.
 
Wei, X., Gong, B., Liu, Z., Lu, W., Wang, L. (2018). Improving the improved training of wasserstein gans: a consistency term and its dual effect. arXiv preprint arXiv:1803.01541.
 
Wu, K., Qiang, Y., Song, K., Ren, X., Yang, W., Zhang, W., Hussain, A., Cui, Y. (2020). Image synthesis in contrast MRI based on super resolution reconstruction with multi-refinement cycle-consistent generative adversarial networks. Journal of Intelligent Manufacturing, 31(5), 1215–1228.
 
Yu, Z., Zhai, Y., Han, X., Peng, T., Zhang, X.-Y. (2021). MouseGAN: GAN-based multiple MRI modalities synthesis and segmentation for mouse brain structures. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer, pp. 442–450.
 
Yurt, M., Dar, S.U., Erdem, A., Erdem, E., Oguz, K.K., Çukur, T. (2021). mustGAN: multi-stream generative adversarial networks for MR image synthesis. Medical Image Analysis, 70, 101944.
 
Zhang, D., Huang, G., Zhang, Q., Han, J., Han, J., Wang, Y., Yu, Y. (2020). Exploring task structure for brain tumor segmentation from multi-modality MR images. IEEE Transactions on Image Processing, 29, 9032–9043.
 
Zhang, H., Li, H., Dillman, J.R., Parikh, N.A., He, L. (2022). Multi-contrast MRI image synthesis using switchable cycle-consistent generative adversarial networks. Diagnostics, 12(4), 816.
 
Zhang, J., Chi, Y., Lyu, J., Yang, W., Tian, Y. (2023). Dual arbitrary scale super-resolution for multi-contrast MRI. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, pp. 282–292.
 
Zhu, J.-Y., Park, T., Isola, P., Efros, A.A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232.

Biographies

Nguyen Van Hieu
https://orcid.org/0000-0001-5311-806X
nvhieuqt@dut.udn.vn

H. Nguyen Van is a senior lecturer at the University of Danang – University of Science and Technology. He obtained his PhD from the Saint Petersburg State Institute of Technology and his MSc and BSc degrees from Saint Petersburg State University, Russia. Over the past five years, he has published a number of research papers on the development of machine learning and deep learning models and their applications. His research interests include artificial intelligence, optimization, decision-making, and computational intelligence.

Phan Minh Nhat
https://orcid.org/0009-0005-1717-3842
nhat0299@gmail.com

N. Phan Minh is a junior researcher at the Department of Software Engineering, The University of Danang – University of Science and Technology. His research interests are data science, machine learning, and deep learning, with a special focus on near-infrared spectroscopy, probabilistic models, and 2D to 3D image processing. He is an undergraduate student at the University of Danang – University of Science and Technology in Vietnam with a specialization in data science and artificial intelligence.

Ngo Le Huy Hien
https://orcid.org/0000-0002-1439-8289
hien.ngo160203@vnuk.edu.vn

H. Ngo Le Huy is a postgraduate researcher at the School of Built Environment, Engineering, and Computing, Leeds Beckett University, United Kingdom. He obtained an MSc in information and technology at Leeds Beckett University under the Erasmus Mundus in green networking and cloud computing program. During the last five years, he has published research papers mainly related to the advancements in machine learning and deep learning models and their applications. His research interests include artificial intelligence, green ICT, and sustainable computing.

Le Hoang Ngoc Han
https://orcid.org/0009-0004-1065-1015
102240003@hv.dut.udn.vn

H. Le Hoang Ngoc is a junior researcher at the Department of Software Engineering, The University of Danang – University of Science and Technology. Her research interests are data science and computer vision, with a special focus on MRI image processing. She obtained her BSc from the University of Danang – University of Science and Technology in Vietnam with a specialization in data science and artificial intelligence.


Full article PDF XML
Full article PDF XML

Copyright
© 2026 Vilnius University
Open access article under the CC BY license.

Keywords
SynthModDiff denoising diffusion probabilistic models MRI synthesis image-to-image translation

Metrics
since January 2020
256

Article info
views

77

Full article
views

62

PDF
downloads

21

XML
downloads


Share


RSS