Hybrid Deep Learning Architecture for Retinal Vessel Segmentation: Integrating Attention U-Net and Resunet on the CHASEDB1 Dataset

International Journal of Electronics and Communication Engineering

© 2026 by SSRG - IJECE Journal

Volume 13 Issue 2

Year of Publication : 2026

Authors : K. S. Pandiyan, U. Palani

10.14445/23488549/IJECE-V13I2P117

How to Cite?

K. S. Pandiyan, U. Palani, "Hybrid Deep Learning Architecture for Retinal Vessel Segmentation: Integrating Attention U-Net and Resunet on the CHASEDB1 Dataset," SSRG International Journal of Electronics and Communication Engineering, vol. 13,  no. 2, pp. 225-238, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I2P117

Abstract:

The computer-aided diagnosis of ophthalmologic diseases, including diabetic retinopathy, glaucoma, and high blood pressure-related retinopathy, depends on retinal vessel segmentation as a key precondition. This study proposes HybridNet, a new deep learning network that combines spatial attention features of Attention U-Net and residual learning features of ResUNet to perform better and distinguish vessels more accurately. The framework adopts a complete preprocessing pipeline that features Contrast Limited Adaptive Histogram Equalization (CLAHE), Gaussian filtering, and intensity normalization to advance the image quality before segmentation. The dual-branch structure has the advantage of channel-wise feature combining via a 1 x 1 convolution layer, which can extract complementary features of attention-guided spatial-wise and context-wise features retained by the residual module. Optimization of the Model was accomplished through a composite loss that uses Binary Cross-Entropy (α =0.7) and Dice loss (β =0.3), trained using the Adam optimizer and adaptive learning rate scheduling over fifty epochs. Experimental optimization on the CHASEDB1 dataset proves its high performance with a Dice coefficient of 0.884, IoU of 0.797, precision of 0.885, recall of 0.877, and AUC-ROC of 0.918. This outperforms baseline designs by +2.8% Dice score and +1.6% IoU. The Data flow modeling is a Crow Foot Notation Entity-Relationship Diagram (ERD) structure that represents the connections and interactions between the users, training sessions, models, metrics, and visual outputs. The results validate that HybridNet performs better than the sum of its parts, in that fine vessel structures, bifurcations, and crossovers are accurately segmented, and background noise is reduced. The framework is shown to have high feasibility in clinical use with automated ocular diagnosis, with its balanced accuracy and computational efficiency in its fast detection.

Keywords:

Retinal vessel segmentation, Attention U-Net, ResUNet, CHASEDB1, Hybrid Deep Learning, Medical image analysis, Semantic segmentation.

References:

[1] Chukwuebuka Joseph Ejiyi et al., “Attention-Enriched Deeper UNet (ADU-NET) for Disease Diagnosis in Breast Ultrasound and Retina Fundus Images,” Progress in Artificial Intelligence, vol. 13, pp. 351-366, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] D.E. Alvarado-Carrillo, and O.S. Dalmau-Cedeño, “Width Attention-based Convolutional Neural Network for Retinal Vessel Segmentation,” Expert Systems with Applications, vol. 209, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] D. Li, and S. Rahardja, “BSEResU-Net: An Attention-based Before-Activation Residual U-Net for Retinal Vessel Segmentation,” Computer Methods and Programs in Biomedicine, vol. 205, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Jihyoung Ryu et al., “SegR-Net: A Deep Learning Framework with Multi-Scale Feature Fusion for Robust Retinal Vessel Segmentation,” Computers in Biology and Medicine, vol. 163, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Kasikrit Damkliang et al., “Binary Semantic Segmentation for Detection of Prostate Adenocarcinoma using an Ensemble with Attention and Residual U-Net Architectures,” PeerJ Computer Science, vol. 9, pp. 1-29, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Anuj Kumar Pandey, Satya Prakash Singh, and Chinmay Chakraborty, “Residual Attention UNet GAN Model for Enhancing the Intelligent Agents in Retinal Image Analysis,” Service Oriented Computing and Applications, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Lei Yang et al., “A Hybrid Deep Segmentation Network for Fundus Vessels Via Deep-Learning Framework,” Neurocomputing, vol. 448, pp. 168-178, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] M. Krithika alias AnbuDevi, and K. Suganthi, “Review of Semantic Segmentation of Medical Images using Modified Architectures of UNET,” Diagnostics, vol. 12, no. 12, pp. 1-31, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Nouf Saeed Alotaibi, “Micro Aneurysm Detection using Optimized Residual‐based Temporal Attention Convolutional Neural Network with Inception‐V3 Transfer Learning,” Microscopy Research and Technique, vol. 87, no. 5, pp. 908-921, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Shun Zhao et al., “Attention Residual Convolution Neural Network based on U-net (AttentionResU-Net) for Retina Vessel segmentation,” IOP Conference Series Earth and Environmental Science, vol. 440, pp. 1-9, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Wenhuan Liu et al., “RFARN: Retinal Vessel Segmentation based on Reverse Fusion Attention Residual Network,” PLoS ONE, vol. 16, no. 12, pp. 1-33, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Yibo Wan et al., “Retinal Blood Vessels Segmentation with Improved SE‐UNET Model,” International Journal of Imaging Systems and Technology, vol. 34, no. 4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yan Xu et al., “Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches,” Bioengineering, vol. 11, no. 10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ziqiang Gao et al., “A Retinal Vessel Segmentation Network Approach based on Rough Sets and Attention Fusion Module,” Information Sciences, vol. 678, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ziaur Rahman, Ruihong Zhang, and Jameel Ahmed Bhutto, “A Symmetrical Approach to Brain Tumor Segmentation in MRI using Deep Learning and Threefold Attention Mechanism,” Symmetry, vol. 15, no. 10, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Zekun Wang, Yanni Zou, and Peter X. Liu, “Hybrid Dilation and Attention Residual U-Net for Medical Image Segmentation,” Computers in Biology and Medicine, vol. 134, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Sushma Nagdeote, and Sapna Prabhu, “Hybrid UNet Architecture based on Residual Learning of Fundus Images for Retinal Vessel Segmentation,” Journal of Physics Conference Series, vol. 2070, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] J. Han, Y. Wang, and H. Gong, “Fundus Retinal Vessels Image Segmentation Method Based on Improved U-Net,” IRBM, vol. 43, no. 6, pp. 628-639, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] ZhenChao Cui et al., “MF2ResU-Net: A Multi-Feature Fusion Deep Learning Architecture for Retinal Blood Vessel Segmentation,” Research Square, pp. 1-24, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Yanming Guo, “Augmentation is AUtO-Net: Augmentation-Driven Contrastive Multiview Learning for Medical Image Segmentation,” arXiv Preprint, pp. 1-80, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Anil Kumar Bondala, and Kranthi Kumar Lella, “Revolutionizing Diabetic Retinopathy Detection using DB-SCA-UNet with Drop Block-Based Attention Model in Deep Learning for Precise Analysis of Color Retinal Images,” The European Physical Journal Special Topics, vol. 234, pp. 3563-3583, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Paresh Chandra Sau, Manish Gupta, and Atul Bansal, “Optimized RESUNET++-Enabled Blood Vessel Segmentation for Retinal FUNDUS Image based on Hybrid Meta-Heuristic Improvement,” International Journal of Image and Graphics, vol. 24, no. 3, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Fatema Tuj Johora Faria et al., “Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images,” arXiv Preprint, pp. 1-39, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Jiajia Ni et al., “FSE-Net: Rethinking the Up-Sampling Operation in Encoder-Decoder Structure for Retinal Vessel Segmentation,” Biomedical Signal Processing and Control, vol. 90, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Nianzu Lv et al., “TCDDU-Net: Combining Transformer and Convolutional Dual-path Decoding U-Net for Retinal Vessel Segmentation,” Scientific Reports, vol. 14, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Chengyang Du, Jie Zhuang, and Xinglu Huang, “Deep Learning Technology in Vascular Image Segmentation and Disease Diagnosis,” Journal of Intelligent Medicine, vol. 1, no. 1, pp. 6-41, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Sanli Yi et al., “Segmentation of Retinal Vessels based on MRANet,” Heliyon, vol. 9, no. 1, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Tanishq Soni et al., “Retinal Vessel Segmentation using Multi Scale Feature Attention with MobileNetV2 Encoder,” Scientific Reports, vol. 15, pp. 1-22, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Fernando Daniel Hernandez-Gutierrez et al., “Retinal Vessel Segmentation Based on a Lightweight U-Net and Reverse Attention,” Mathematics, vol. 13, no. 13, pp. 1-27, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Ruihong Zhang, and Guosong Jiang, “Exploring a Multi-path U-net with Probability Distribution Attention and Cascade Dilated Convolution for Precise Retinal Vessel Segmentation in Fundus Images,” Scientific Reports, vol. 15, pp. 1-20, 2025.[CrossRef] [Google Scholar] [Publisher Link]