Abstract
Segmenting retinal vessels plays a significant role in the diagnosis of fundus disorders. However, there are two problems in the retinal vessel segmentation methods. First, fine-grained features of fine blood vessels are difficult to be extracted. Second, it is easy to lose track of the details of blood vessel edges. To solve the problems above, the Residual SimAM Pyramid-Spatial Attention Unet (RSP-SA Unet) is proposed, in which the encoding, decoding, and upsampling layers of the Unet are mainly improved. Firstly, the RSP structure proposed in this paper approximates a residual structure combined with SimAM and Pyramid Segmentation Attention (PSA), which is applied to the encoding and decoding parts to extract multi-scale spatial information and important features across dimensions at a finer level. Secondly, the spatial attention (SA) is used in the upsampling layer to perform multi-attention mapping on the input feature map, which could enhance the segmentation effect of small blood vessels with low contrast. Finally, the RSP-SA Unet is verified on the CHASE_DB1, DRIVE, and STARE datasets, and the segmentation accuracy (ACC) of the RSP-SA Unet could reach 0.9763, 0.9704, and 0.9724, respectively. Area under the ROC curve (AUC) could reach 0.9896, 0.9858, and 0.9906, respectively. The RSP-SA Unet overall performance is better than the comparison methods.
Graphical Abstract
Similar content being viewed by others
References
Wang H, Xu G, Pan X et al (2022) Attention-inception-based U-Net for retinal vessel segmentation with advanced residual [J]. Comput Electr Eng 98:107670
Zana F, Klein JC (1999) A multimodal registration algorithm of eye fundus images using vessels detection and Hough transform [J]. IEEE Trans Med Imaging 18(5):419–428
Sinthanayothin C (1999) Automated localization of the optic disc, fovea, and retinal blood vessels from digital colour fundus images [J]. Br J Ophthalmal 83:231–238
Nardini JT, Pugh CWJ, Byrne HM (2023) Statistical and topological summaries aid disease detection for segmented retinal vascular images[J]. Microcirculation 30(4):e12799
Lisha LB, Helen Sulochana C (2023) Highly accurate blood vessel segmentation using texture‐based modified K‐means clustering with deep learning model[J]. Concurr Comput: Pract Exp 35(7):e7590
Häner NU, Dysli C, Munk MR (2023) Imaging in retinal vascular disease: A review[J]. Clin Exp Ophthalmol 51(3):217–228
Shen Y, Li J, Zhu W et al (2023) Graph attention U-Net for retinal layer surface detection and choroid neovascularization segmentation in OCT images[J]. IEEE Transactions on Medical Imaging
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 234–241
Mookiah MRK, Hogg S, MacGillivray TJ et al (2021) A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification [J]. Med Image Anal 68:101905
Zhang Y, Fang J, Chen Y et al (2022) Edge-aware U-net with gated convolution for retinal vessel segmentation [J]. Biomed Signal Process Control 73:103472
Liu R, Wang T, Zhang X et al (2023) DA-Res2UNet: explainable blood vessel segmentation from fundus images [J]. Alex Eng J 68:539–549
Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, et al (2018) Unet++: A nested u-net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4. Springer International Publishing, 3–11
Zhou Y, Yu H, Shi H (2021) Study group learning: Improving retinal vessel segmentation trained with noisy labels[C]//Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer International Publishing, 57–67
Chen J, Lu Y, Yu Q, et al (2021) Transunet: Transformers make strong encoders for medical image segmentation[J]. arXiv preprint arXiv:2102.04306
Yang L, Wang H, Zeng Q et al (2021) A hybrid deep segmentation network for fundus vessels via deep-learning framework [J]. Neurocomputing 448:168–178
Ma D, Lu D, Chen S et al (2021) LF-UNet–a novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images [J]. Comput Med Imaging Graph 94:101988
Li H, Fang J, Liu S et al (2019) Cr-unet: a composite network for ovary and follicle segmentation in ultrasound images [J]. IEEE J Biomed Health Inform 24(4):974–983
Boudegga H, Elloumi Y, Akil M et al (2021) Fast and efficient retinal blood vessel segmentation method based on deep learning network [J]. Comput Med Imaging Graph 90:101902
Chen D, Yang W, Wang L et al (2022) PCAT-UNet: UNet-like network fused convolution and transformer for retinal vessel segmentation [J]. PLoS ONE 17(1):e0262689
Liu Y, Shen J, Yang L et al (2023) ResDO-UNet: a deep residual network for accurate retinal vessel segmentation from fundus images [J]. Biomed Signal Process Control 79:104087
Du H, Zhang X, Song G et al (2023) Retinal blood vessel segmentation by using the MS-LSDNet network and geometric skeleton reconnection method [J]. Comput Biol Med 153:106416
Sun K, Chen Y, Chao Y et al (2023) A retinal vessel segmentation method based improved U-Net model [J]. Biomed Signal Process Control 82:104574
Li J, Gao G, Liu Y et al (2023) MAGF-Net: a multiscale attention-guided fusion network for retinal vessel segmentation [J]. Measurement 206:112316
Yang L, Zhang RY, Li L, et al (2021) Simam: A simple, parameter-free attention module for convolutional neural networks[C]//International conference on machine learning. PMLR 11863–11874
Guo C, Szemenyei M, Yi Y, et al (2021) Sa-unet: Spatial attention u-net for retinal vessel segmentation[C]//2020 25th international conference on pattern recognition (ICPR). IEEE, 1236–1242
Alom MZ, Hasan M, Yakopcic C, et al (2018) Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation[J]. arXiv preprint arXiv:1802.06955
Guo S, Wang K, Kang H et al (2019) BTS-DSN: deeply supervised neural network with short connections for retinal vessel segmentation [J]. Int J Med Informatics 126:105–113
Wang B, Qiu S, He H (2019) Dual encoding u-net for retinal vessel segmentation[C]//Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part I 22. Springer International Publishing, 84–92
Jin Q, Meng Z, Pham TD et al (2019) DUNet: a deformable network for retinal vessel segmentation [J]. Knowl-Based Syst 178:149–162
Laibacher T, Weyde T, Jalali S (2019) M2u-net: Effective and efficient retinal vessel segmentation for real-world applications[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 0-0
Wang D, Haytham A, Pottenburgh J et al (2020) Hard attention net for automatic retinal vessel segmentation [J]. IEEE J Biomed Health Inform 24(12):3384–3396
Zhuang J (2018) LadderNet: Multi-path networks based on U-Net for medical image segmentation[J]. arXiv preprint arXiv:1810.07810
Zheng S, Jayasumana S, Romera-Paredes B, et al (2015) Conditional random fields as recurrent neural networks[C]//Proceedings of the IEEE international conference on computer vision. 1529–1537
Hu J, Wang H, Gao S et al (2019) S-unet: a bridge-style u-net framework with a saliency mechanism for retinal vessel segmentation [J]. IEEE Access 7:174167–174177
Wang N, Li K, Zhang G et al (2023) Improvement of retinal vessel segmentation method based on U-Net [J]. Electronics 12(2):262
Li L, Verma M, Nakashima Y, et al (2020) Iternet: Retinal image segmentation utilizing structural redundancy in vessel networks[C]//Proceedings of the IEEE/CVF winter conference on applications of computer vision. 3656–3665
Takikawa T, Acuna D, Jampani V, et al (2019) Gated-scnn: Gated shape cnns for semantic segmentation[C]//Proceedings of the IEEE/CVF international conference on computer vision. 5229–5238
Zhang J, Zhang Y, Xu X. (2021) Pyramid u-net for retinal vessel segmentation [C]ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE: 1125–1129.
Xu GX, Ren CX (2023) SPNet: a novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss [J]. Neurocomputing 523:199–212
Wei S, Sun X, Zhao H, et al. (2021) RSAN: residual subtraction and attention network for single image super-resolution [C]//2020 25th International Conference on Pattern Recognition (ICPR). IEEE: 1–6.
Oliveira A, Pereira S, Silva CA (2018) Retinal vessel segmentation based on fully convolutional neural networks [J]. Expert Syst Appl 112:229–242
Maninis KK, Pont-Tuset J, Arbeláez P, et al. (2016) Deep retinal image understanding [C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer International Publishing. 140-148
Tong H, Fang Z, Wei Z et al (2021) SAT-Net: a side attention network for retinal image segmentation [J]. Appl Intell 51(7):5146–5156
Ren K, Chang L, Wan M et al (2022) An improved U-net based retinal vessel image segmentation method [J]. Heliyon 8(10):e11187
Li J, Zhang T, Zhao Y, et al. (2022) MC-UNet: multimodule concatenation based on U-shape network for retinal blood vessels segmentation [J]. Computational Intelligence and Neuroscience. 2022
Guo C, Szemenyei M, Hu Y, et al. (2021) Channel attention residual u-net for retinal vessel segmentation [C]//ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE: 1185–1189.
Alom MZ, Yakopcic C, Hasan M et al (2019) Recurrent residual U-Net for medical image segmentation [J]. Journal of Medical Imaging 6(1):014006–014006
Wang C, Zhao Z, Ren Q et al (2019) Dense U-net based on patch-based learning for retinal vessel segmentation [J]. Entropy 21(2):168
Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation [J]. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495
Khan TM, Alhussein M, Aurangzeb K et al (2020) Residual connection-based encoder decoder network (RCED-Net) for retinal vessel segmentation [J]. IEEE Access 8:131257–131272
Guo C, Szemenyei M, Yi Y, et al. (2021) Sa-unet: spatial attention u-net for retinal vessel segmentation [C]//2020 25th international conference on pattern recognition (ICPR). IEEE: 1236–1242.
Sathananthavathi V, Indumathi G (2021) Encoder enhanced atrous (EEA) Unet architecture for retinal blood vessel segmentation [J]. Cogn Syst Res 67:84–95
Lu J, Xu Y, Chen M et al (2018) A coarse-to-fine fully convolutional neural network for fundus vessel segmentation [J]. Symmetry 10(11):607
Wu Y, Xia Y, Song Y et al (2020) NFN+: a novel network followed network for retinal vessel segmentation [J]. Neural Netw 126:153–162
Li X, Jiang Y, Li M et al (2020) Lightweight attention convolutional neural network for retinal vessel image segmentation [J]. IEEE Trans Industr Inf 17(3):1958–1967
Funding
The authors acknowledge the support from the National Natural Science Foundation of China under Grant No. 62205091, the Postdoctoral Science Foundation of China under Grant No. 2022M710983, the Heilongjiang Provincial Postdoctoral Foundation Grant No. LBH-Z22201, and the Fundamental Research Foundation for Universities of Heilongjiang Province under Grant No. 2022-KYYWF-0121.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
Not required.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, K., Chen, Y., Dong, F. et al. Retinal vessel segmentation method based on RSP-SA Unet network. Med Biol Eng Comput 62, 605–620 (2024). https://doi.org/10.1007/s11517-023-02960-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-023-02960-6