Secure and optimized ViT–Trans GAN architecture: A mathematical modeling approach for encrypted MRI brain image reconstruction
*Priyanka SharmaCorresponding authorvipri24@gmail.comDepartment of Computer Science and EngineeringPoornima UniversityJaipur, Rajasthan, 303905, IndiaView full profile → , Bright Keswanibright.keswani@poornima.edu.inDepartment of Computer Science and EngineeringPoornima UniversityJaipur, Rajasthan, 303905, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Jan 2026
- Published Online:
- 31 Aug 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2234
- Pages:
- 2917–2929
Abstract
The growing use of Magnetic Resonance Imaging (MRI) in brain disorder diagnosis requires reliable methods for both data security and image quality preservation during transmission and storage. To address these challenges, this study proposes a secure image reconstruction framework based on a hybrid Vision Transformer and TransGAN (ViT–TransGAN) model for encrypted MRI brain images. The proposed architecture exploits the long-range dependency learning capability of Vision Transformers along with the generative strength of TransGAN to effectively recover meaningful structural details from encrypted inputs. A mathematical formulation is employed to represent the encryption process, reconstruction mechanism, and optimization objectives, contributing to stable model training and improved reconstruction accuracy. The effectiveness of the proposed method is validated using standard MRI brain datasets, and its performance is compared with existing convolutional neural network and GAN-based approaches. Experimental results demonstrate noticeable improvements in reconstruction quality measured by It is found that proposed ViT+ TransGAN achieves 11.74 of MSE, 40.09 of PSNR, 0.7774 of SSIM, 0.167 of FSIM, -0.9657 of NRMSE, 0.9181 of VIF, 0.8846 of DSC for degradation. Moreover, 13.04 of MSE, 37.20 of PSNR, 0.8691 of SSIM, 0.164 of FSIM, -1.4517 of NRMSE, 0.9642 of VIF and 0.8815 of DSC for reconstructiona.
Keywords
Subject Classifications
References
[1] F. Aamir, I. Aslam, M. Arshad, and H. Omer, “Accelerated diffusion-weighted MR image reconstruction using deep neural networks,” J. Digit. Imaging, vol. 36, no. 1, pp. 276–288 (2023), doi: 10.1007/s10278-022-00709-5.
[2] Z. Alagic, J. D. Cardenas, K. Halldorsson, V. Grozman, S. Wallgren, C. Suzuki, J. Helmenkamp, and S. K. Koskinen, “Deep learning versus iterative image reconstruction algorithm for head CT in trauma,” Emerg. Radiol., vol. 29, pp. 339–352 (2022), doi: 10.1007/s10140-021-02012-2.
[3] M. Arshad, F. Najeeb, R. Khawaja, A. Ammar, K. Amjad, and H. Omer, “Cardiac MR image reconstruction using cascaded hybrid dual domain deep learning framework,” PLoS One, vol. 20, no. 1, Art. no. e0313226 (2025), doi: 10.1371/journal.pone.0313226.
[4] C. Cao, W. Huang, F. Hu, and X. Gao, “Hierarchical neural architecture search with adaptive global–local feature learning for magnetic resonance image reconstruction,” Comput. Biol. Med., vol. 168, Art. no. 107774 (2024), doi: 10.1016/j.compbiomed.2023.107774.
[5] E. Z. Chen, P. Wang, X. Chen, T. Chen, and S. Sun, “Pyramid convolutional RNN for MRI image reconstruction,” IEEE Trans. Med. Imaging, vol. 41, no. 8, pp. 2033–2047 (2022), doi: 10.1109/TMI.2022.3153849.
[6] M. Z. Darestani, V. Nath, W. Li, Y. He, H. R. Roth, Z. Xu, D. Xu, R. Heckel, and C. Zhao, “IR-FRestormer: Iterative refinement with Fourier-based Restormer for accelerated MRI reconstruction,” in Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis. (WACV), pp. 7655–7664 (2024).
[7] V. D. Gowda, Y. N. Sunitha, S. V. Chakrasali, K. D. V. Prasad, P. Sarma, and M. Rahman, “Mathematical analysis of wavelet-based multi-image compression in medical diagnostics,” J. Discrete Math. Sci. Cryptogr., vol. 27, no. 2-B, pp. 675–687 (2024), doi: 10.47974/JDMSC-1912.
[8] A. Hossain, M. T. Islam, S. K. Abdul Rahim, M. A. Rahman, T. Rahman, H. Arshad, A. Khandakar, M. A. Ayari, and M. E. Chowdhury, “A lightweight deep learning based microwave brain image network model for brain tumor classification using reconstructed microwave brain (RMB) images,” Biosensors, vol. 13, no. 2, Art. no. 238 (2023), doi: 10.3390/bios13020238.
[9] J. Hsieh, E. Liu, B. Nett, J. Tang, J.-B. Thibault, and S. Sahney, New Era of Image Reconstruction: TrueFidelity™ Technical White Paper on Deep Learning Image Reconstruction. Chicago, IL, USA: GE Healthcare (2019).
[10] L. Kang, B. Tang, J. Huang, and J. Li, “3D-MRI super-resolution reconstruction using multi-modality based on multi-resolution CNN,” Comput. Methods Programs Biomed., vol. 248, Art. no. 108110 (2024), doi: 10.1016/j.cmpb.2024.108110.
[11] I. Kim, H. Kang, H. J. Yoon, B. M. Chung, and N.-Y. Shin, “Deep learning-based image reconstruction for brain CT: Improved image quality compared with adaptive statistical iterative reconstruction-Veo (ASIR-V),” Neuroradiology, vol. 63, pp. 905–912 (2021).
[12] Y. T. Lan, K. Ren, Y. Wang, W. L. Zheng, D. Li, B. L. Lu, and L. Qiu, “Seeing through the brain: Image reconstruction of visual perception from human brain signals,” arXiv preprint arXiv:2308.02510 (2023).
[13] N. Lee, H.-H. Cho, S. M. Lee, and S. K. You, “Adaptation of deep learning image reconstruction for pediatric head CT: A focus on the image quality,” J. Korean Soc. Radiol., vol. 84, pp. 240–252 (2023).
[14] J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool, and R. Timofte, “SwinIR: Image restoration using Swin Transformer,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. Workshops (ICCVW), pp. 1833–1844 (2021), doi: 10.1109/ICCVW54120.2021.00210.
[15] A. Noonia, D. Thakral, P. Mathur, F. Sheth, H. Shaikh, and A. K. Gupta, “A discrete mathematical model and cryptography for secure medical image analysis: Encrypted chest X-ray classification,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-A, pp. 1473–1486 (2025), doi: 10.47974/JDMSC-2146.
[16] C. Oh, J.-Y. Chung, and Y. Han, “Domain transformation learning for MR image reconstruction from dual domain input,” Comput. Biol. Med., vol. 170, Art. no. 108098 (2024), doi: 10.1016/j.compbiomed.2024.108098.
[17] A. S. Rao and K. Mahantesh, “Impact of computer vision based secure image enrichment techniques on image classification model,” J. Discrete Math. Sci. Cryptogr., vol. 26, no. 3, pp. 899–911 (2023), doi: 10.47974/JDMSC-1777.
[18] P. Sprawls, “AAPM tutorial: CT image detail and noise,” Radiographics, vol. 12, pp. 1041–1046 (1992).
[19] L. Sun, S. Yu, C. Zhang, and X. Ding, “Exploring Siamese networks in self-supervised fast MRI reconstruction,” arXiv preprint arXiv:2501.10851 (2025).
[20] M. A. Talukder, M. M. Islam, M. A. Uddin, A. Akhter, M. A. J. Pramanik, S. Aryal, M. A. A. Almoyad, K. F. Hasan, and M. A. Moni, “An efficient deep learning model to categorize brain tumor using reconstruction and fine-tuning,” Expert Syst. Appl., vol. 230, Art. no. 120534 (2023).
[21] J. Wang, J. Chen, D. Chen, and J. Wu, “Large window-based Mamba U-Net for medical image segmentation: Beyond convolution and self-attention,” arXiv preprint arXiv:2403.07332 (2024).
[22] Y. Yan, T. Yang, X. Zhao, C. Jiao, A. Yang, and J. Miao, “DC-SiamNet: Deep contrastive Siamese network for self-supervised MRI reconstruction,” Comput. Biol. Med., vol. 167, Art. no. 107619 (2023).
[23] H. Zhang, Y. Shinomiya, and S. Yoshida, “3D MRI reconstruction based on 2D generative adversarial network super-resolution,” Sensors, vol. 21, no. 9, Art. no. 2978 (2021).
[24] “Brain tumor classification (MRI) dataset,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri. [Accessed: Jun. 19, 2026].
