MDA-Net: Multi-Dimensional Attention Network for Retinal Vessel Segmentation
DOI:
https://doi.org/10.63313/CS.8007Keywords:
Feature Enhancement, Feature Fusion, UNet, Attention MechanismAbstract
Fundus images play an important role in the diagnosis and treatment of ophthalmic diseases (such as hypertension, arteriosclerosis and diabetic retinopathy), and the morphological infor-mation of retinal blood vessels can be used as an important index for the diagnosis of these dis-eases, so it is very important for accurate segmentation of retinal blood vessels. With the con-tinuous development of computer technology, deep learning method provides a new idea for medical image segmentation. Due to the complex structure and different scales of retinal blood vessels, the existing U-Net model still faces significant challenges in dealing with these tasks. To solve these problems, we propose a retinal vascular segmentation network MDA-Net based on multidimensional attention mechanism. Based on the U-Net structure, this method optimizes the network design by reducing the number of encoder-decoder layers to three layers, and intro-duces the Coordinate Grouped Feature Fusion (CGFF), multi-dimensional feature enhancement (MDFE) and multi-scale convolution enhancement (MSCE). Firstly, CGFF module integrates mul-ti-scale features by grouping convolution and multi-dimensional pooling, which improves the adaptability of the model to uneven distribution of blood vessels. Secondly, MDFE module com-bines channel shuffling, multi-dimensional attention and pooling operation to enhance the ex-traction ability of micro-vessel features, especially in low contrast and complex back-ground.Experimental results show that the accuracy (ACC), sensitivity (SE) and specificity (SP) of this method DRIVE 0.9825, 0.9842 and 0.9895, 0.8211, 0.8342 and 0.8452 respectively, and 0.9840, 0.9872 and 0.992 respectively. MDA-Net proposed in this paper provides a new idea and scheme for improving the performance of retinal blood vessel segmentation.
References
[1] Huang Z, Fang Y, Huang H, et al. Automatic Retinal Vessel Segmentation Based on an Improved U-Net Approach [J]. Scientific Programming, 2021, 55(34):3219.
[2] Wild S, Roglic G, Green A, et al. Global prevalence of diabetes estimates for the year 2000 and projection for 2030 [J]. Diabetes care, 2004, 27(5): 1047-1053.
[3] J. Dong, Y. Cong, G. Sun, D. Hou, Semantic-transferable weakly-supervised endoscopic lesions segmentation, in Proc IEEE Int Conf Comput Vision (2019),Seoul, Korea, pp. 10712-10721. [Online]. Available: https://openaccess.thecvf.com/content_ICCV_2019/papers/Dong_Semantic-Transferable_Weakly-Supervised_Endoscopic_Lesions_Segmentation_ICCV_2019_paper.pdf.
[4] Edita, Dervisevic, Suzana, et al. Challenges In Early Glaucoma Detection [J]. Medical archives (Sarajevo, Bosnia and Herzegovina), 2016, 70(3): 7-203.
[5] Bibiloni P, González-Hidalgo M, Massanet S. A real-time fuzzy morphological algorithm for retinal vessel seg-mentation[J]. Journal of Real-Time Image Processing, 2019, 16(6): 2337–2350.
[6] Fraz M M, Barman S A, Remagnino P, Hoppe A, Basit A, Uyyanonvara B, Rudnicka A R, Owen C G. An approach to localize the retinal blood vessels using bit planes and centerline detection[J].Computer Methods and Programs in Biomedicine, 2012, 108(2): 600–616.
[7] Hassan G, El-Bendary N, Hassanien A E, Fahmy A, Abullah M. S, Snasel V. Retinal blood vessel segmentation approach based on mathematical morphology[J]. Procedia Computer Science, 2015, 65: 612–622.
[8] Yin Y, Adel M, Bourennane S. Retinal vessel segmentation using a probabilistic tracking method[J]. Pattern Recognition, 2012, 45(4): 1235–1244. 67.
[9] NayebifarB, Moghaddamh. A .A novel method for retinal vessel tracking using particle filters[J].Computers in Bi-ology and Medicine, 2013.DOI:10.1016/j.compbiomed.2013.01.016.
[10] Zhao J, Yang J, Ai D, Song H, Jiang Y, Huang Y, Zhang L, Wang Y. Automatic retinal vessel segmentation using multi-scale superpixel chain tracking[J]. Digital Signal Processing, 2018, 81: 26–42.
[11] Al-Rawi M, Qutaishat M, Arrar M. An improved matched filter for blood vessel detection of digital retinal images[J]. Computers in Biology and Medicine, 2007, 37(2): 262–267.
[12] Wang Y, Ji G, Lin P, Trucco E. Retinal vessel segmentation using multiwavelet kernels and multiscale hierarchical decomposition[J]. Pattern Recognition, 2013, 46(8): 2117– 2133.
[13] Oliveira W S, Teixeira J V, Ren T I, Cavalcanti G D C, Sijbers J. Unsupervised retinal vessel segmentation using combined filters[J]. PLOS ONE, 2016, 11(2): e0149943.
[14] Frangi A F, Niessen W J, Vincken K L, et al. Multiscale vessel enhancement filtering[C]//Medical Image Computing and Computer-Assisted Intervention—MICCAI’ 98: First International Conference Cambridge, MA, USA, October 11 – 13, 1998 Proceedings 1. Springer Berlin Heidelberg, 1998: 130-137.
[15] Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille A L and Zhou Y 2021 TransU-Net: Transformers make strong encoders for medical image segmentation (arXiv:2102.04306).
[16] Oktay O, Schlemper J, Folgoc L L, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla N Y and Kainz B 2018 Attention U-Net: Learning where to look for the pancreas (arXiv:1804.03999).
[17] Alom M Z, Hasan M, Yakopcic C, Taha T M and Asari V K 2018 Recurrent residual convolutional neural network based on U-Net (R2UNet) for medical image segmentation (arXiv:1802.06955).
[18] Zhou Z, Rahman Siddiquee, et al. UNet++: A nested UNet architecture for medical image segmentation[J]. Proc. Int. Workshop on Deep Learning in Medical Image Analysis and MultimodalLearning for Clinical Decision Support, 2018, 18(2): 3-11.
[19] Zhang, Y., Mao, Q., Tian, Y., Wang, W., Ren, L., & Li, H. (2025). Dual-path information enhanced pyramid U-Net for COVID-19 lung infection segmentation. Engineering Applications of Artificial Intelligence, 142, 109977.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
