A Deep Learning-Based MRI-to-CT Image Translation Using Generative Models
DOI:
https://doi.org/10.70112/ajeat-2026.15.2.4365Keywords:
MRI-to-CT Translation, Deep Learning, Generative Adversarial Networks , Diffusion Models, Medical Image Synthesis, Image-to-image Translation, Convolutional Neural Networks, Cross-modality LearningAbstract
Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are both widely used medical imaging, they provide complementary diagnostic clues. Still getting both of them at the same time, ends up taking more time, more money, and for CT also involves radiation exposure, which is not small. Lately, deep learning has really pushed things forward, with cross-modality synthesis where a CT image can be created straight from an MRI scan. In this paper, there is a survey of deep learning based MRI-to-CT translation strategies, with attention on “generate it” style methods such as Generative Adversarial Networks (GANs) and diffusion models. The discussion goes into how models trade accuracy versus realism, plus what kinds of optimization tricks are usually used and what limitations show up in real practice. At the end, it also shares thoughts on upcoming research directions, like how to make the approach more stable and easier to deploy.
References
[1] Q. Lyu and G. Wang, “Conversion between ct and mri images using diffusion and score-matching models,” IEEE Transactions, 2020.
[2] S. Nikitha, H. P. Sudhanva, T. A. Nayana, L. Varshini, S. V. Pandurangi, and P. Soukar, “An ai-based system for pneumonia detection in chest x-rays using deep learning models,” Asian Journal of Engineering and Applied Technology, vol. 14, no. 1, pp. 7–13, 2025.
[3] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” inAdvances in Neural Information Processing Systems (NeurIPS), 2014.
[4] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[5] J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.
[6] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in ICLR, 2015.
[7] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[8] T. Karras, S. Laine, and T. Aila, “A style-based generator architecture for gans,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[9] A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional gans,” in ICLR, 2016.
[10] P. Dhariwal and A. Nichol, “Diffusion models beat gans on image synthesis,” in NeurIPS, 2021.
[11] A. Nichol and P. Dhariwal, “Improved denoising diffusion probabilistic models,” in ICML, 2021.
[12] H. Yang, J. Sun, H. Carass, Z. Xu, C. Zhao, and J. L. Prince, “Unpaired brain mr-to-ct synthesis using a structure-constrained cyclegan,” IEEE Transactions on Medical Imaging, 2018.
[13] R. Graf, J. Schmitt, and S. S. et al., “Denoising diffusion-based mri to ct image translation enables automated spinal segmentation,” European Radiology Experimental, 2023.
[14] A. Moschetto, L. Puglisi, A. Sargood, P. Dell’Acqua, F. Guarnera,
[15] S. Battiato, and D. Ravi, “Benchmarking gans, diffusion models, and flow matching for t1w-to-t2w mri translation,” arXiv preprint, 2025.
[16] Y. Jin and W. L. et al., “Deep learning based ct image generation from mri using cnn,” IEEE Access, 2019.
[17] J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, “Unpaired image-toimage translation using cycle-consistent adversarial networks,” in IEEE International Conference on Computer Vision (ICCV), 2017.
[18] M. Nie, L. Trullo, J. Lian, C. Petitjean, and S. Ruan, “Medical image synthesis with context-aware generative adversarial networks,” Medical Image Analysis, 2017.
[19] D. Kingma and M. Welling, “Auto-encoding variational bayes,” in ICLR, 2014.
[20] S. Ulyanov, D. Vedaldi, and V. Lempitsky, “Instance normalization: The missing ingredient for fast stylization,” arXiv preprint, 2016.
[21] J. Song and S. Ermon, “Generative modeling by estimating gradients of the data distribution,” in NeurIPS, 2019.
[22] Y. Song and S. Ermon, “Score-based generative modeling through stochastic differential equations,” in ICLR, 2021.
[23] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in MICCAI, 2015.
[24] K. Armanious, C. Jiang, and M. F. et al., “Medgan: Medical image translation using gans,” Computerized Medical Imaging and Graphics, 2020.
[25] Z. Chartsias, T. Joyce, M. Giuffrida, and S. A. Tsaftaris, “Multimodal mr synthesis via modality-invariant latent representation,” IEEE Transactions on Medical Imaging, 2018.
[26] H. Zhao, O. Gallo, I. Frosio, and J. Kautz, “Loss functions for image restoration with neural networks,” IEEE Transactions, 2017.
[27] H. Emami, M. Dong, S. P. Nejad-Davarani, and C. K. Glide-Hurst, “Sagan: Structure-aware gan for organ-preserving synthetic ct generation,” arXiv preprint, 2021.
[28] Y. Wolterink, T. Leiner, M. Viergever, and I. Isgum, “Deep mr to ct synthesis using unpaired data,” Medical Image Analysis, 2017.
[29] L. Hiasa, Y. Otake, and N. T. et al., “Cross-modality image synthesis from unpaired data using cyclegan,” Medical Imaging Conference, 2018.
[30] Z. Huang and N. Wang, “Data augmentation techniques in medical imaging,” IEEE Access, 2020.
[31] F. Milletari, N. Navab, and S. Ahmadi, “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 3DV, 2016.
[32] S. Chen, K. Ma, and Y. Zheng, “Med3d: Transfer learning for 3d medical image analysis,” arXiv preprint, 2019.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Centre for Research and Innovation
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
