Abstract
Accurate cerebral vascular endothelium segmentation in Optical Coherence Tomography (OCT) images is crucial for cerebrovascular disease assessment, yet remains challenging due to the extreme thinness of endothelial structures and the scarcity of high-quality annotations. In this work, we make two key contributions. First, we construct a high-quality cerebral vascular OCT dataset with meticulous manual annotations provided by experienced experts, offering a reliable foundation for supervised learning and quantitative evaluation. Second, we propose a novel segmentation framework based on a Dual Coordinate Attention (DCA) mechanism, which explicitly integrates Cartesian and polar coordinate representations to capture complementary structural cues of vascular endothelium. Extensive experiments demonstrate that the proposed DCA-based network consistently outperforms representative baseline models in terms of Dice and HD95. Ablation studies further validate the effectiveness of the DCA module and identify its optimal deployment strategy. Overall, this work provides a robust automated solution for cerebral vascular endothelium segmentation in OCT images, with potential value for cerebrovascular research and clinical assessment.
Data availability
The dataset generated and analyzed during the current study is not publicly available due to patient privacy but is available from the corresponding author on reasonable request. The source code used in this study is available at: https://github.com/Glaz-j/DCA-Net.
References
Figueredo, A. J. & Wolf, P. S. A. Assortative pairing and life history strategy—A cross-cultural study. Hum. Nat. 20, 317–330. https://doi.org/10.1007/s12110-009-9068-2 (2009).
Hao, Z., AghaKouchak, A., Nakhjiri, N., Farahmand, A. Global integrated drought monitoring and prediction system (GIDMaPS) data sets. figshare. http://dx.doi.org/10.6084/m9.figshare.853801 (2014).
Feigin, V. L. et al. Global, regional, and national burden of stroke and its risk factors, 1990–2019: A systematic analysis for the Global Burden of Disease Study 2019. Lancet Neurol. 20(10), 795–820 (2021).
Xu, R. et al. Optical coherence tomography in cerebrovascular disease: Open up new horizons. Transl. Stroke Res. 14(2), 137–145 (2023).
Togao, O. et al. Arterial spin labeling-based MR angiography for cerebrovascular diseases: Principles and clinical applications. J. Magn. Reson. Imaging 60(4), 1305–1324 (2024).
Wu, C., Xu, X. & Wang, R. Application of CT angiography in the diagnosis of acute cerebrovascular disease in neurology. J. Med. Imaging Health Inform. 11(3), 878–885 (2021).
Aumann, S., Donner, S., Fischer, J., Müller, F. Optical coherence tomography (OCT): principle and technical realization. In High Resolution Imaging in Microscopy and Ophthalmology: New Frontiers in Biomedical Optics, 59–85 (2019).
Kugelman, J. et al. A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation. Sci. Rep. 12(1), 14888 (2022).
Li, J. et al. Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images. Biomed. Opt. Express 12(4), 2204–2220 (2021).
Fan, Y. et al. RMAP-ResNet: Segmentation of brain tumor OCT images using residual multicore attention pooling networks for intelligent minimally invasive theranostics. Biomed. Signal Process. Control 90, 105805 (2024).
Quintana-Quintana, O. J. et al. Dual U-Net-based conditional generative adversarial network for blood vessel segmentation with reduced cerebral MR training volumes. Micromachines 13(6), 823 (2022).
Chollet, E. et al. Neurovascular segmentation in sOCT with deep learning and synthetic training data. arXiv preprint arXiv:2407.01419, (2024).
Ronneberger, O., Fischer, P., Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, vol. 18, 234–241 (2015).
Tanthanathewin, R. et al. Automatic exudate and aneurysm segmentation in OCT images using UNET++ and hyperreflective-foci feature based bagged tree ensemble. PLoS One 19(5), e0304146 (2024).
Melinšćak, M. Attention-based U-net: Joint segmentation of layers and fluids from retinal OCT images. In 2023 46th MIPRO ICT and Electronics Convention (MIPRO), 391–396 (2023).
Chen, L. et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018).
Cheng, H. et al. Multi-object segmentation of coronary artery OCT images based on multi-scale deeping learning method. In 2023 42nd Chinese Control Conference (CCC), 8388–8393 (2023).
Cao, H. et al. Swin-Unet: Unet-Like pure transformer for medical image segmentation. In Computer Vision—ECCV 2022 Workshops, 205–218 (Springer Nature Switzerland, 2023).
Portegies, M.L.P. et al. Cerebrovascular disease. In Handbook of Clinical Neurology, vol. 138, 239–261 (Elsevier, 2016).
Anagnostakou, V. et al. Optical coherence tomography for neurovascular disorders. Neuroscience 474, 134–144 (2021).
Xiao, Z. et al. Gated channel attention network for cataract classification on AS-OCT image. In Neural Information Processing: 28th International Conference, ICONIP 2021, vol. 28, 357–368 (2021).
Hu, J., Shen, L., Sun, G. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132–7141 (2018).
Jumat, J. et al. A systematic review of attention mechanisms in UNet models for medical image segmentation. In International Conference on Electronic Design, 221–231 (2024).
Zhang, M. et al. A segmentation method of 3D liver image based on multi-scale feature fusion and coordinate attention mechanism. In International Conference on Intelligent Computing, 3–15 (2023).
Lawal, M. & Yi, D. Polar contrast attention and skip cross-channel aggregation for efficient learning in U-Net. Comput. Biol. Med. 181, 109047 (2024).
Chao, L. et al. Dual-domain attention-guided convolutional neural network for low-dose cone-beam computed tomography reconstruction. Knowl.-Based Syst. 251, 109295 (2022).
Liu, Q. et al. DCA-Net: Dual-branch contextual-aware network for auxiliary localization and segmentation of parathyroid glands. Biomed. Signal Process. Control 84, 104856 (2023).
Tearney, G. J. & Bouma, B. E. Optical Coherence Tomography (Elsevier, 2012).
Jones, M. R. et al. Imaging of intracranial atherosclerosis using optical coherence tomography. Am. J. Neuroradiol. 33(3), 509–515 (2012).
Katona, A. & Nyúl, L. G. Automatic lumen and vessel wall segmentation in intravascular ultrasound images using deep learning. IEEE Trans. Med. Imaging 36(7), 1503–1514 (2017).
Zou, S., Zhang, Z., & Gao, G. OCTAMamba: A state-space model approach for precision OCTA vasculature segmentation. arXiv preprintarXiv:2409.08000 (2024).
Bakkouri, I. & Afdel, K. MLCA2F: Multi-level context attentional feature fusion for COVID-19 lesion segmentation from CT scans. SIViP 17(4), 1181–1188. https://doi.org/10.1007/s11760-022-02325-w (2023).
Bakkouri, I. et al. BG-3DM2F: Bidirectional gated 3D multi-scale feature fusion for Alzheimer’s disease diagnosis. Multimed. Tools Appl. 81, 10743–10776. https://doi.org/10.1007/s11042-022-12242-2 (2022).
Bakkouri, I. & Afdel, K. Computer-aided diagnosis (CAD) system based on multi-layer feature fusion network for skin lesion recognition in dermoscopy images. Multimed. Tools Appl. 79, 20483–20518. https://doi.org/10.1007/s11042-019-07988-1 (2020).
Bakkouri, I. & Afdel, K. Multi-scale CNN based on region proposals for efficient breast abnormality recognition. Multimed. Tools Appl. 78, 12939–12960. https://doi.org/10.1007/s11042-018-6267-z (2019).
Umirzakova, S., Shakhnoza, M., Sevara, M. & Whangbo, T. K. Deep learning for multiple sclerosis lesion classification and stratification using MRI. Comput. Biol. Med. 192, 110078 (2025).
Ghosal, P. et al. Compound attention embedded dual channel encoder-decoder for MS lesion segmentation from brain MRI. Multimed. Tools Appl. 84, 31139–31171. https://doi.org/10.1007/s11042-024-20416-3 (2025).
Agarwal, R., Ghosal, P., Sadhu, A. K., Murmu, N. & Nandi, D. Multi-scale dual-channel feature embedding decoder for biomedical image segmentation. Comput. Methods Programs Biomed. 257, 108464. https://doi.org/10.1016/j.cmpb.2024.108464 (2024).
Xie, H. et al. BUT-Net: Boundary-aware U-Net structure with two-path transformers for lesion segmentation in mCNV using OCT images. Expert Syst. Appl. 297, 129405. https://doi.org/10.1016/j.eswa.2025.129405 (2026).
Ghosal, P., Roy, A. & Agarwal, R. U-SwinTrans: Automated skin lesion segmentation using Swin Transformer. Proc. IEEE Int. Symp. Adv. Comput. Commun. ISACC https://doi.org/10.1109/ISACC65211.2025.10969397 (2025).
Kalita, H., Dandapat, S. & Bora, P. K. A generative adversarial network for delineation of retinal interfaces in OCT B-scans with age-related macular degeneration. Biomed. Signal Process. Control 108, 107856. https://doi.org/10.1016/j.bspc.2025.107856 (2025).
Acknowledgements
This work was supported by the Open Research Fund (SCRCND202508) of the Shenzhen Clinical Research Center for Neurological Diseases (LCYSSQ20220823091204009), and the Shenzhen Team on the Fusion of Health Management and Prevention of Neurological Diseases (No. 6099007).
Funding
This work was supported by the Open Research Fund (SCRCND202508) of the Shenzhen Clinical Research Center for Neurological Diseases (LCYSSQ20220823091204009), and the Shenzhen Team on the Fusion of Health Management and Prevention of Neurological Diseases (No. 6099007).
Author information
Authors and Affiliations
Contributions
Z.W. designed the algorithm and conducted the main experiments. Y.S. performed part of the experiments and drafted the main manuscript text. C.H. assisted with data preprocessing and figure preparation. E.Y.K.N. provided technical guidance on imaging methodology and manuscript revision. Q.L. and L.R. contributed to clinical data acquisition and interpretation. J.L. conceived and supervised the study, provided overall project guidance, and finalized the manuscript. All authors reviewed and approved the final version of the manuscript.
Corresponding authors
Ethics declarations
Competing interests
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
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, Z., Shen, Y., Ng, E.Y.K. et al. Dual coordinate attention (DCA) network for accurate cerebral vascular endothelium segmentation in OCT images. Sci Rep (2026). https://doi.org/10.1038/s41598-026-43601-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-43601-w
