MixGANMed: A Novel Hybrid Generative Framework forMulti-Modal Medical Imaging Synthesis

  • Authors

    • Shrina Patel U & P U Patel Department of Computer Engineering, C S Patel Institute of Technology, Charotar University of Science and Technology, Changa-Gujarat, India
    • Dr. Ashwin Makwana U & P U Patel Department of Computer Engineering, C S Patel Institute of Technology, Charotar University of Science and Technology, Changa-Gujarat, India
    https://doi.org/10.14419/78n87617

    Received date: June 17, 2025

    Accepted date: July 18, 2025

    Published date: July 25, 2025

  • Hybrid Generative Adversarial Network; Multi-modal Medical Imaging; Synthetic Image Generation; DCGAN; Conditional GAN

  • Abstract

    This research introduces MixGANMed, a unique hybrid generative adversarial network that synthesizes images of both grayscale and RGB ‎types in medical images. Combining methods from DC-GAN, Conditional-GAN, and SR-GAN allows the architecture to improve areas of ‎stability, guided by labels and quality for humans. Evaluations were carried out across several datasets, for example, Pneumonia X-ray, ‎Diabetic Retinopathy, Brain Tumor MRI, Leukemia using WBC microscopy images, and Skin Cancer observed with Dermoscopy. While ‎ordinary GAN models needed more epochs to show results and performed poorly, MixGANMed improved the system and showed low ‎losses after only a fraction of the training time. This model achieved good results, preserving structure and image faithfulness at faster ‎speeds than the other evaluated architectures. The images include all the main anatomical and pathological information, making it possible to ‎see that the model works well to synthesize realistic medical pictures. The research shows that MixGANMed creates high-quality multi-‎modal medical images, offering practical applications for data augmentation, formatting synthetic datasets, and training diagnostic models ‎when data is scarce‎.

  • References

    1. Akbar, M.U., W. Wang and A. Eklund. 2023. Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images. Machine Learning: Science and Technology, 6(1): 15022. https://doi.org/10.1088/2632-2153/ad9a3a.
    2. Afnaan, K., T. Singh and P. Duraisamy. 2024. Hybrid deep learning framework for bidirectional medical image synthesis. In 2024 15th Interna-tional Conference on Computing Communication and Networking Technologies, ICCCNT 2024, 1–6. https://doi.org/10.1109/ICCCNT61001.2024.10725975.
    3. Ali, M., M. Ali, M. Hussain and D. Koundal. 2024. Generative Adversarial Networks (GANs) for medical image processing: Recent advancements. Archives of Computational Methods in Engineering, 1–14. https://doi.org/10.1007/s11831-024-10174-8.
    4. Chen, Y. et al. 2024. ICycle-GAN: Improved cycle generative adversarial networks for liver medical image generation. Biomedical Signal Pro-cessing and Control, 92: 106100. https://doi.org/10.1016/j.bspc.2024.106100.
    5. Devi, Y.S. and S. Phani Kumar. 2023. Diabetic retinopathy (DR) image synthesis using DCGAN and classification of DR using transfer learning approaches. International Journal of Image and Graphics, 24(05): 2340009. https://doi.org/10.1142/S0219467823400090.
    6. Dugas, E., Jared, Jorge and W. Cukierski. 2015. Diabetic retinopathy detection. Kaggle. Available: https://kaggle.com/competitions/diabetic-retinopathy-detection. Accessed: Feb. 9, 2024.
    7. Fanconi, A. 2021. Skin cancer: Malignant vs. benign. Kaggle. Available: https://www.kaggle.com/datasets/fanconic/skin-cancer-malignant-vs-benign. Accessed: Apr. 21, 2025.
    8. Fard, A.S., D.C. Reutens, S.C. Ramsay, S.J. Goodman, S. Ghosh and V. Vegh. 2024. Image synthesis of interictal SPECT from MRI and PET us-ing machine learning. Frontiers in Neurology, 15: 1383773. https://doi.org/10.3389/fneur.2024.1383773.
    9. Friedrich, P., Y. Frisch and P.C. Cattin. 2024. Deep generative models for 3D medical image synthesis. In Generative Machine Learning Models in Medical Image Computing, Springer, 255–278. Available: http://arxiv.org/abs/2410.17664. https://doi.org/10.1007/978-3-031-80965-1_13.
    10. Hamghalam, M. and A.L. Simpson. 2024. Medical image synthesis via conditional GANs: Application to segmenting brain tumours. Computers in Biology and Medicine, 170: 107982. https://doi.org/10.1016/j.compbiomed.2024.107982.
    11. Heng, Y., M. Yinghua, F.G. Khan, A. Khan and Z. Hui. 2024. HLSNC-GAN: Medical image synthesis using hinge loss and switchable normaliza-tion in CycleGAN. IEEE Access, 12: 55448–55464. https://doi.org/10.1109/ACCESS.2024.3390245.
    12. Islam, S. et al. 2024. Generative Adversarial Networks (GANs) in medical imaging: Advancements, applications, and challenges. IEEE Access, 12: 35728–35753. https://doi.org/10.1109/ACCESS.2024.3370848.
    13. Jha, A. and H. Iima. 2024. CT to MRI image translation using CycleGAN: A deep learning approach for cross-modality medical imaging. In Inter-national Conference on Agents and Artificial Intelligence, 3: 951–957. https://doi.org/10.5220/0012422900003636.
    14. Kermany, D.S. et al. 2018. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5): 1122–1131.e9. https://doi.org/10.1016/j.cell.2018.02.010.
    15. Kumar, M., A.S. Chivukula and G. Barua. 2025. Deep learning-based encryption scheme for medical images using DCGAN and virtual planet do-main. Scientific Reports, 15(1): 1211. https://doi.org/10.1038/s41598-024-84186-6.
    16. Madhav, S., T.M. Nandhika and M.K. Kavitha Devi. 2024. Super resolution of medical images using SRGAN. In 2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024, 1–6. https://doi.org/10.1109/ic-ETITE58242.2024.10493588.
    17. Mamo, A.A., B.G. Gebresilassie, A. Mukherjee, V. Hassija and V. Chamola. 2024. Advancing medical imaging through generative adversarial net-works: A comprehensive review and future prospects. Cognitive Computation, 16(5): 2131–2153. https://doi.org/10.1007/s12559-024-10291-3.
    18. Mooney, P. 2018. Chest X-ray images (Pneumonia). Kaggle. Available: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia. Accessed: Feb. 9, 2024.
    19. Nandal, P., S. Pahal, A. Khanna and P.R. Pinheiro. 2024. Super-resolution of medical images using real ESRGAN. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3497002.
    20. Paul, N. 2019. Brain MRI images for brain tumor detection. Kaggle. Available: https://www.kaggle.com/datasets/navoneel/brain-mri-images-for-brain-tumor-detection. Accessed: Apr. 21, 2025.
    21. Raad, R. et al. 2024. Conditional generative learning for medical image imputation. Scientific Reports, 14(1): 171. https://doi.org/10.1038/s41598-023-50566-7.
    22. Sai Akhil, M.C., B.S. Sanjana Sharma, A. Kodipalli and T. Rao. 2024. Medical image synthesis using DCGAN for chest X-ray images. In 2024 In-ternational Conference on Knowledge Engineering and Communication Systems, ICKECS 2024, 1(1): 1–8. https://doi.org/10.1109/ICKECS61492.2024.10617031.
    23. Sherwani, M.K. and S. Gopalakrishnan. 2024. A systematic literature review: Deep learning techniques for synthetic medical image generation and their applications in radiotherapy. Frontiers in Radiology, 4: 1385742. https://doi.org/10.3389/fradi.2024.1385742.
    24. Shah, D., M.A. Ullah Khan and M. Abrar. 2024. Reliable breast cancer diagnosis with deep learning: DCGAN-driven mammogram synthesis and validity assessment. Applied Computational Intelligence and Soft Computing, 2024(1): 1122109. https://doi.org/10.1155/2024/1122109.
    25. Sindhura, D.N., R.M. Pai, S.N. Bhat and M.M.M. Pai. 2024. A review of deep learning and generative adversarial networks applications in medical image analysis. Multimedia Systems, 30(3): 161. https://doi.org/10.1007/s00530-024-01349-1.
    26. Tanwar, V. 2022. Leukemia cancer small dataset. Kaggle. Available: https://www.kaggle.com/datasets/visheshtanwar26/leukemia-cancer-small-dataset/data. Accessed: Apr. 21, 2025.
    27. Varshitha, S., N. Lavanya, M. Shirisha, S. Manmatti, K.P. Asha Rani and S. Gowrishankar. 2024. Enhancing medical imaging resolution: Exploring SRGAN for high-quality medical image reconstruction. In Proceedings of ICWITE 2024: IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, 1–8. https://doi.org/10.1109/ICWITE59797.2024.10503215.
    28. Wang, J. et al. 2025. Self-improving generative foundation model for synthetic medical image generation and clinical applications. Nature Medicine, 31(2): 609–617. https://doi.org/10.1038/s41591-024-03359-y.
    29. Wang, R., A.F. Heimann, M. Tannast and G. Zheng. 2024. CycleSGAN: A cycle-consistent and semantics-preserving generative adversarial net-work for unpaired MR-to-CT image synthesis. Computerized Medical Imaging and Graphics, 117: 102431. https://doi.org/10.1016/j.compmedimag.2024.102431.
    30. Zakaria, R., H. Abedlamjid, D. Zitouni and A. Elqaraoui. 2024. Medical-DCGAN: Deep convolutional GAN for medical imaging. In Advances in Emerging Financial Technology and Digital Money, CRC Press, 123–134. https://doi.org/10.1201/9781032667478-10.

  • Downloads

  • How to Cite

    Patel, S. ., & Makwana, D. A. . (2025). MixGANMed: A Novel Hybrid Generative Framework forMulti-Modal Medical Imaging Synthesis. International Journal of Basic and Applied Sciences, 14(3), 277-285. https://doi.org/10.14419/78n87617