Journal of Innovative Image Processing
IRO Journals
Volume 8 — Issue 2 — June 2026

Depthwise Residual Transformer for Retinal Vascular Enhancement using Fundus Images

https://doi.org/10.36548/jiip.2026.2.003
Pages: 487-500
  • Srinivas Rangu , Srinivas Rangu
    Department of Electronics and Communication Engineering, Central University of Karnataka, India
    Department of Electronics and Communication Engineering, Central University of Karnataka, India
  • Uday Patil Uday Patil
    Department of Electrical Engineering, Central University of Karnataka, India
    Department of Electrical Engineering, Central University of Karnataka, India
  • &  Nagaraj Yamanakkanavar Nagaraj Yamanakkanavar
    Department of Electronics and Communication Engineering, Central University of Karnataka, India
    Department of Electronics and Communication Engineering, Central University of Karnataka, India
PDF
PDF

How to Cite

Rangu, Srinivas, Uday Patil, and Nagaraj Yamanakkanavar. 2026. “Depthwise Residual Transformer for Retinal Vascular Enhancement Using Fundus Images”. Journal of Innovative Image Processing 8 (2): 487-500. https://doi.org/10.36548/jiip.2026.2.003.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Fundus Image Enhancement
— Transformer
— Depthwise Convolution
— Deep Learning
Published: 09-04-2026

Abstract

The high-quality visual information in fundus images enables highly accurate clinical judgment for the diagnosis of eye diseases. The image quality subsequently suffers due to factors such as refractive media excretions and inconsistent patient cooperation. To avoid these conditions, we propose a depthwise residual (DWR) transformer-based enhancement network for distorted fundus images. The proposed framework contains four blocks: the DWR block, the encoder block, the transformer block, and the decoder block. The DWR block is designed to improve model generalization over noisy inputs by applying channel-wise filtering. The encoder block has convolutional filters to capture fine-grained local features from the input images. The transformer block effectively captures global dependencies from the encoder blocks. The decoder block works for spatial resolution reconstruction while concatenating contextual features from the encoder with fine-grained information for accurate localization. The proposed model performance is evaluated through both subjective and objective analysis on open--source datasets such as DRIVE, STARE, CHASE_DB1, HRF, and MESSIDOR. Our proposed method achieves an excellent SSIM of 0.901 with the DRIVE dataset and PSNR of 31.596 with the MESSIDOR dataset, surpassing state–of–the–art methods across all datasets.

References

  1. Alqahtani, Fasial Majed, Somaya Adwan, Mohd Yazed Ahmad, Salmah Binti Karman, Rasha Maged, and Lamya'A. Maged. "Impact of Retinal Enhancement Techniques on Blood Vessel Segmentation." In 2024 IEEE 14th Symposium on Computer Applications & Industrial Electronics (ISCAIE), IEEE, 2024, 517-521.
  2. Bandara, A. M. R. R., and P. W. G. R. M. P. B. Giragama. "A Retinal Image Enhancement Technique for Blood Vessel Segmentation Algorithm." In 2017 IEEE international conference on industrial and information systems (ICIIS), IEEE, 2017, 1-5.
  3. Pal, Mahua Nandy, Minakshi Banerjee, and Shuvankar Roy. "Deep Learning Supported Evaluation of Retinal Vessel Enhancement Techniques." In Advances in Data Science and Computing Technology, Apple Academic Press, 2022, 3-18.
  4. Liao, Miao, Shao-Wei Zheng, and Yu-Qian Zhao. "A Novel Method for Retinal Vascular Image Enhancement." Journal of Optoelectronics Laser 23, no. 11 (2012): 2237-2242.
  5. Abdushkour, Hesham, Toufique A. Soomro, Ahmed Ali, Fayyaz Ali Jandan, Herbert Jelinek, Farida Memon, Faisal Althobiani, Saleh Mohammed Ghonaim, and Muhammad Irfan. "Enhancing Fine Retinal Vessel Segmentation: Morphological Reconstruction and Double Thresholds Filtering Strategy." PLoS One 18, no. 7 (2023): e0288792.
  6. Shabbir, Safia, Anam Tariq, and M. Usman Akram. "A Comparison and Evaluation of Computerized Methods for Blood Vessel Enhancement and Segmentation in Retinal Images." International Journal of Future Computer and Communication 2, no. 6 (2013): 600.
  7. Hien, Nguyen Mong. "Retinal Vessels Segmentation Based on Enhancing Multi-scale Line Detection." In International Conference on the Development of Biomedical Engineering in Vietnam, Cham: Springer Nature Switzerland, 2022, 519-528.
  8. Soomro, Toufique Ahmed, Ahmed J. Afifi, Ahmed Ali Shah, Shafiullah Soomro, Gulsher Ali Baloch, Lihong Zheng, Ming Yin, and Junbin Gao. "Impact of Image Enhancement Technique on CNN Model for Retinal Blood Vessels Segmentation." IEEE Access 7 (2019): 158183-158197.
  9. Chollet, François. "Xception: Deep Learning with Depthwise Separable Convolutions." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, 1251-1258.
  10. Gonzalez, Rafael C, “Digital Image Processing”, Pearson Education India, 2009.
  11. Hatamizadeh, Ali, Yucheng Tang, Vishwesh Nath, Dong Yang, Andriy Myronenko, Bennett Landman, Holger R. Roth, and Daguang Xu. "Unetr: Transformers for 3d Medical Image Segmentation." In Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2022, 574-584.
  12. Chen, Tianhua, and Mike Lucock. "The Mental Health of University Students During the COVID-19 Pandemic: An Online Survey in the UK." PloS one 17, no. 1 (2022): e0262562.
  13. Liang, Liming, Baohe Lu, Jian Wu, Yulin Li, and Xiaoqi Sheng. "Sfit-Net: Spatial Reconstruction Feature Interaction Transformer Retinal Vessel Segmentation Algorithm." Biomedical Signal Processing and Control 106 (2025): 107688.
  14. Lv, Nianzu, Li Xu, Yuling Chen, Wei Sun, Jiya Tian, and Shuping Zhang. "Tcddu-Net: Combining Transformer and Convolutional Dual-Path Decoding U-Net for Retinal Vessel Segmentation." Scientific Reports 14, no. 1 (2024): 25978.
  15. Jiang, Ligang, Jing Hu, Zhuoran Wang, Guohui Yuan, Chongjun Huang, Zhiming Xiong, Meizhen Zhang, Weihua Yang, and Yuhua Tong. "TransDualSegNet: Transformer Dual Segment Network for Retinal Vasculature Segmentation in OCT." Quantitative Imaging in Medicine and Surgery 15, no. 10 (2025): 9338.
  16. Mehmood, Mehwish, Majed Alsharari, Shahzaib Iqbal, Ivor Spence, and Muhammad Fahim. "Retinalitenet: A Lightweight Transformer Based CNN for Retinal Feature Segmentation." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024, 2454-2463.
  17. Lin, Ji, Xingru Huang, Huiyu Zhou, Yaqi Wang, and Qianni Zhang. "Stimulus-Guided Adaptive Transformer Network for Retinal Blood Vessel Segmentation in Fundus Images." Medical Image Analysis 89 (2023): 102929.
  18. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-Net: Convolutional Networks for Biomedical Image Segmentation." In International Conference on Medical image computing and computer-assisted intervention, Cham: Springer international publishing, 2015, 234-241.
  19. Soni, Ashish, Radhakanta Koner, and Vasanta Govind Kumar Villuri. "M-Unet: Modified U-Net Segmentation Framework with Satellite Imagery." In Proceedings of the Global AI congress 2019, Singapore: Springer Singapore, 2020, 47-59.
  20. Gurrola-Ramos, Javier, Oscar Dalmau, and Teresa E. Alarcón. "A Residual Dense U-Net Neural Network for Image Denoising." IEEE Access 9 (2021): 31742-31754.
  21. Luo, Xuebing, Lingxi Peng, Ziyan Ke, Jinhui Lin, and Zhiwen Yu. "Pa-Net: A Hybrid Architecture for Retinal Vessel Segmentation." Pattern Recognition 161 (2025): 111254.
  22. Chen, Long, Changan Yuan, Huafu Xu, Ye He, and Jianhui Jiang. "Robust Denoising of Structure Noise Through Dual-Diffusion Brownian Bridge Modeling and Coupled Sampling." Electronics 14, no. 21 (2025): 4243.
  23. Staal, Joes, Michael D. Abràmoff, Meindert Niemeijer, Max A. Viergever, and Bram Van Ginneken. "Ridge-Based Vessel Segmentation in Color Images of the Retina." IEEE transactions on medical imaging 23, no. 4 (2004): 501-509.
  24. Ibtehaz, Nabil, and M. Sohel Rahman. "MultiResUNet: Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation." Neural networks 121 (2020): 74-87.
  25. Fraz, Muhammad Moazam, Paolo Remagnino, Andreas Hoppe, Bunyarit Uyyanonvara, Alicja R. Rudnicka, Christopher G. Owen, and Sarah A. Barman. "An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation." IEEE transactions on biomedical engineering 59, no. 9 (2012): 2538-2548.
  26. Chen, Haoyu, and Kyungbaek Kim. "Multi-Convolutional Channel Residual Spatial Attention U-Net for Industrial and Medical Image Segmentation." IEEE Access 12 (2024): 76089-76101.
  27. Decencière, Etienne, Xiwei Zhang, Guy Cazuguel, Bruno Lay, Béatrice Cochener, Caroline Trone, Philippe Gain et al. "Feedback on a Publicly Distributed Image Database: the Messidor Database." Image Analysis & Stereology (2014): 231-234.
  28. Liang, Haoyi, and Daniel S. Weller. "Comparison-Based Image Quality Assessment for Selecting Image Restoration Parameters." IEEE transactions on image processing 25, no. 11 (2016): 5118-5130.
  29. Zhang, Kai, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising." IEEE transactions on image processing 26, no. 7 (2017): 3142-3155.