International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Advancing Medical Imaging: High-Fidelity Reconstruction with SRGAN |
|---|---|
| ABSTRACT | High-resolution medical imaging is essential for accurate diagnosis and clinical decision-making; however, real-world constraints such as acquisition time, patient movement, and radiation exposure often limit the achievable quality. This paper presents a two-stage Super-Resolution Generative Adversarial Network (SRGAN) designed to generate high-fidelity medical images from low-resolution inputs. The first stage reconstructs coarse high-resolution outputs, while the second stage refines anatomical textures and enhances structural fidelity. The system incorporates VGG19-based perceptual loss to preserve high-level semantic features and utilizes ResNet50 as an auxiliary feature-comparison network to ensure structural consistency across anatomical regions. A custom training strategy combining adversarial, perceptual, content, and refinement losses enables stable multi-stage optimization. Experimental observations indicate substantial improvements in perceived sharpness, edge clarity, and diagnostic detail compared to interpolation and single-stage SR models. Hypothetical quantitative evaluation suggests the model can achieve superior PSNR, SSIM, and visual realism. The proposed system demonstrates strong potential for enhancing MRI, CT, and X-ray modalities while maintaining computational feasibility. Future research may extend this approach to multimodal super-resolution, lightweight clinical deployment, and uncertainty-aware reconstructions. |
| AUTHOR | SPOORTHI P A, DR. MALA SWADI, MADHU SHREE S, JATIN SONI Assistant Professor, Department of ECE, Dr. Ambedkar Institute of Technology, Bengaluru, India Department of ECE, Dr. Ambedkar Institute of Technology, Bengaluru, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312056 |
| pdf/56_Advancing Medical Imaging High-Fidelity Reconstruction with SRGAN.pdf | |
| KEYWORDS | |
| References | [1] C. Ledig, L. Theis, F. Huszár, et al., “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4681–4690. [2] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015, pp. 234–241. [3] J. You, J. Jin, L. Zhang, and Y. Zhang, “CT Super Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE),” in IEEE Transactions on Medical Imaging, vol. 39, no. 1, pp. 188–203, Jan. 2020. [4] F. Armanious, C. Jiang, M. Fischer, et al., “MedGAN: Medical Image Translation using GANs,” in Computerized Medical Imaging and Graphics, vol. 79, 2020. [5] J. Kim, J. Kwon Lee, and K. Mu Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1646–1654. [6] B. Wang, Y. Zhou, D. Zhang, et al., “Enhanced Super-Resolution Generative Adversarial Network for Histopathology Image Restoration,” in Computers in Biology and Medicine, vol. 130, 2021. [7] Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu, “Residual Dense Network for Image Super-Resolution,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2472–2481. [8] S. M. Ali, K. Shah, and S. A. Khan, “Comparative Analysis of Deep Learning Models for Brain Tumor Classification and Detection,” in Journal of Healthcare Engineering, vol. 2021, Article ID 6645938, 2021. [9] The Cancer Imaging Archive (TCIA), “Public Brain Tumor MRI Dataset (BraTS),” Available: https://www.cancerimagingarchive.net/ [10] F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1251–1258. [11] Gong, M., Chen, S., Chen, Q., Zeng, Y., & Zhang, Y. (2021). Generative adversarial networks in medical image processing. Current Pharmaceutical Design, 27(15), 1856-1868. [12] Gupta, R., Sharma, A., & Kumar, A. (2020). Super-resolution using gans for medical imaging. Procedia Computer Science, 173, 28-35. [13] Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., ... & Zhang, K. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. cell, 172(5), 1122-1131. |
