📄 Sciences Methods and Technologies
International Journal (SciMeTech)

Volume 2 · Issue 1 · 2026
ISSN: 3085-5284
Deep Learning-Based Diagnosis-Guided Framework for High-Quality Medical Image Super-Resolution
Km Annoo, Amit Sharma, Suman Pandey
Pages 161–170 · Department of Computer Science and Engineering, Vivekananda Global University, Jaipur, India
⬇ PDF
Abstract
Medical image quality plays a crucial role in accurate disease diagnosis. However, due to limitations in imaging devices and acquisition conditions, medical images are often captured at low resolution, which can negatively affect clinical interpretation. To address this issue, this paper proposes a diagnosis-guided super-resolution framework that enhances both image quality and diagnostic performance.

The proposed model integrates two interconnected components: a super-resolution network and a disease diagnosis network. Unlike conventional approaches that focus solely on visual enhancement, the proposed method incorporates diagnostic feedback to guide the image reconstruction process. A diagnosis-guided attention mechanism is introduced to ensure that the model focuses on clinically relevant regions during enhancement. Additionally, deformable convolution is employed to effectively capture irregular anatomical structures. Experiments conducted on multiple medical imaging datasets demonstrate that the proposed framework significantly improves both image reconstruction quality and diagnostic accuracy, as measured by PSNR, SSIM, and classification performance. The results indicate that integrating super-resolution with diagnosis guidance leads to more reliable and clinically meaningful outcomes.
Keywords: Medical image super-resolution, diagnosis-guided attention, deformable convolution, Alzheimer's disease diagnosis

References

  1. H. Lee, et al., Super-Resolution of Medical Images using Deep Learning with Attention Mechanism, in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2025.
  2. N. Saraei, et al., Deep Learning Techniques in Computer-Aided Diagnosis: A Review, in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2025.
  3. Y. Jia et al., Learning to See the Unseen: Deep Learning for Medical Image Super-Resolution, in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2025.
  4. Y. Xiao, et al., Deep Learning-Based Medical Image Segmentation with Application to Ultrasound Images, in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2025.
  5. G. Aswini, et al., Improved Medical Image Super-Resolution using Deep Residual Dense Network, in Int. Conf. on Information, Communication and Computing Technology, Jun. 2024, pp. 1-10.
  6. J. Huang, et al., Medical Image Super-Resolution via Deep Learning for Diagnosis, in Int. Conf. on Information, Communication and Computing Technology, Jun. 2024, pp. 11-20.
  7. Y. Chen, et al., Deep Learning for Medical Image Super-Resolution, in Int. Conf. on Signal Processing, Jun. 2023, pp. 1-10.
  8. G. Zhou, et al., Deep Learning in Medical Imaging Segmentation: A Review, in Int. Conf. on Information Science, Communication and Networking, Jun. 2021, pp. 1-10.
  9. D. Patel and V. Mankodia, Medical Image Super-Resolution using CNN: An Overview, in Int. Conf. on Information Science, Communication and Networking, Jun. 2023, pp. 11-20.
  10. L. Ahishakiye, et al., Deep Learning-Based Image Reconstruction Methods for Medical Imaging, Journal of Imaging, vol. 7, no. 6, pp. 1-20, 2021.
  11. Y. Sui, O. Afacan, A. Gholipour, and S. K. Warfield, MRI Super-Resolution through Generative Degradation Learning, in Proc. MICCAI, vol. 12906, 2021, pp. 430-440.
  12. J. A. Kennedy, O. Israel, A. Frenkel, R. Bar-Shalom, and H. Azhari, Super-Resolution in PET Imaging, IEEE Trans. Med. Imaging, vol. 25, no. 2, pp. 137-147, 2006.
  13. C. Dong, C. C. Loy, K. He, and X. Tang, Learning a Deep Convolutional Network for Image Super-Resolution, in Proc. ECCV, vol. 8692, 2014, pp. 184-199.
  14. C. Dong, C. C. Loy, and X. Tang, Accelerating the Super-Resolution Convolutional Neural Network, in Proc. ECCV, vol. 9906, 2016, pp. 391-407.
  15. W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution, in Proc. CVPR, 2017, pp. 5835-5843.
  16. B. Lim, S. Son, H. Kim, S. Nah, and K. M. Lee, Enhanced Deep Residual Networks for Single Image Super-Resolution, in Proc. CVPR Workshops, 2017, pp. 1132-1140.
  17. S. Maeda, Unpaired Image Super-Resolution using Pseudo-Supervision, in Proc. CVPR, 2020, pp. 288-297.
  18. J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool, and R. Timofte, SwinIR: Image Restoration using Swin Transformer, in Proc. ICCV Workshops, 2021, pp. 1833-1844.
  19. Y. Gu, et al., MedSRGAN: Medical Image Super-Resolution using Generative Adversarial Networks, Multimedia Tools Appl., vol. 79, no. 29-30, pp. 21815-21840, 2020.
  20. Z. Chen, X. Guo, C. Yang, B. Ibragimov, and Y. Yuan, Joint Spatial-Wavelet Dual-Stream Network for Medical Image Super-Resolution, in Proc. MICCAI, vol. 12265, 2020, pp. 184-193.
  21. Z. Chen, X. Guo, P. Y. M. Woo, and Y. Yuan, Super-Resolution Enhanced Medical Image Diagnosis with Sample Affinity Interaction, IEEE Trans. Med. Imaging, vol. 40, no. 5, pp. 1377-1389, 2021.
  22. M. S. Rad, et al., SROBB: Targeted Perceptual Loss for Single Image Super-Resolution, in Proc. ICCV, 2019, pp. 2710-2719.
  23. N. C. Fox and J. M. Schott, Imaging Cerebral Atrophy: Normal Ageing to Alzheimer's Disease, The Lancet, vol. 363, no. 9406, pp. 392-394, 2004.
  24. C. Misra, Y. Fan, and C. Davatzikos, Baseline and Longitudinal Patterns of Brain Atrophy in MCI Patients and Their Use in Prediction of Short-Term Conversion to AD, NeuroImage, vol. 44, no. 4, pp. 1415-1422, 2009.
  25. J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, and Y. Wei, Deformable Convolutional Networks, in Proc. ICCV, 2017, pp. 764-773.
  26. K. He, X. Zhang, S. Ren, and J. Sun, Deep Residual Learning for Image Recognition, in Proc. CVPR, 2016, pp. 770-778.
  27. J. Kim, J. K. Lee, and K. M. Lee, Accurate Image Super-Resolution using Very Deep Convolutional Networks, in Proc. CVPR, 2016, pp. 1646-1654.
  28. C. Ledig, et al., Photo-Realistic Single Image Super-Resolution using a Generative Adversarial Network, in Proc. CVPR, 2017, pp. 105-114.
  29. S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, CBAM: Convolutional Block Attention Module, in Proc. ECCV, vol. 11211, 2018, pp. 3-19.
  30. Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, Image Super-Resolution using Very Deep Residual Channel Attention Networks, in Proc. ECCV, vol. 11211, 2018, pp. 294-310.
  31. Z. Hui, X. Gao, Y. Yang, and X. Wang, Lightweight Image Super-Resolution with Information Multi-Distillation Network, in Proc. ACM MM, 2019, pp. 2024-2032.
  32. X. Wang, Q. Wang, Y. Zhao, J. Yan, L. Fan, and L. Chen, Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning, in Proc. ACCV, vol. 12623, 2020, pp. 268-285.
  33. X. Zhang, H. Zeng, S. Guo, and L. Zhang, Efficient Long-Range Attention Network for Image Super-Resolution, in Proc. ECCV, vol. 13677, 2022, pp. 649-667.
SciMeTech · Volume 2, Issue 1 · 2026 · ISSN 3085-5284