Optical coherence tomography angiography image segmentation based on multi-scale dilated convolution and dual attention network_Journal of Biomedical Engineering

Authors：

ZENG Qinghao ,  XIAO Zhang , HE Bin , PENG Rushu

School of Mechanical Engineering, University of South China, Hengyang, Hunan 421200, P. R. China;

Corresponding?author：

XIAO Zhang, Email: 2013000885@usc.edu.cn

Keywords：

Optical coherence tomography angiography; Deep learning; Attention mechanism; Image segmentation

DOI：

10.7507/1001-5515.202505030

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Optical coherence tomography angiography (OCTA) is an emerging non-invasive ophthalmic imaging modality. The morphology and contour of the foveal avascular zone (FAZ) are critical biomarkers for the diagnosis of various ophthalmic and systemic diseases; therefore, achieving its accurate segmentation is of substantial clinical significance. To address challenges such as low contrast, indistinct boundaries, and structural confusion with the surrounding retinal vasculature in OCTA images, this paper proposes a multi-scale dilated convolution and dual attention network (MSAD-Net). By integrating a multi-scale dilated convolution module (MSDM) to capture extensive multi-scale contextual information and employing a dual attention module (DAM) to integrate complementary channel and spatial features, thereby synergistically boosting the feature representation of key regions. Experimental results demonstrated that the model achieved superior performance and robust generalization across multiple evaluation metrics, including the Dice similarity coefficient, Jaccard index, precision, and recall—on two public datasets. These findings confirm the robustness of MSAD-Net in the fine segmentation of the FAZ, providing high-precision technical support for the clinical quantitative analysis of ophthalmic diseases.

Citation： ZENG Qinghao, XIAO Zhang, HE Bin, PENG Rushu. Optical coherence tomography angiography image segmentation based on multi-scale dilated convolution and dual attention network. Journal of Biomedical Engineering, 2026, 43(2): 373-381. doi: 10.7507/1001-5515.202505030 Copy

1.	Ang M, Tan A C S, Cheung C M G, et al. Optical coherence tomography angiography: a review of current and future clinical applications. Graefes Arch Clin Exp Ophthalmol, 2018, 256(2): 237-245.
2.	Spaide R F, Fujimoto J G, Waheed N K, et al. Optical coherence tomography angiography. Prog Retin Eye Res, 2018, 64: 1-55.
3.	Abramoff M D, Garvin M K, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng, 2010, 3: 169-208.
4.	Salles M C, Kvanta A, Amrén U, et al. Optical coherence tomography angiography in central retinal vein occlusion: correlation between the foveal avascular zone and visual acuity. Invest Ophthalmol Vis Sci, 2016, 57(9): 242-246.
5.	Linderman R, Salmon A E, Strampe M, et al. Assessing the accuracy of foveal avascular zone measurements using optical coherence tomography angiography: segmentation and scaling. Transl Vis Sci Technol, 2017, 6(3): 16.
6.	Zheng Y, Gandhi J S, Stangos A N, et al. Automated segmentation of foveal avascular zone in fundus fluorescein angiography. Invest Ophthalmol Vis Sci, 2010, 51(7): 3653-3659.
7.	Cheng K K W, Tan B L, Brown L, et al. Macular vessel density, branching complexity and foveal avascular zone size in normal tension glaucoma. Sci Rep, 2021, 11(1): 1056.
8.	Jain K, Pegu J, Bhoot M, et al. Optical coherence tomography angiography of optic disc and macula vessel density in glaucoma and healthy eyes. J Glaucoma, 2019, 28(7): 131-132.
9.	Haddouche A, Adel M, Rasigni M, et al. Detection of the foveal avascular zone on retinal angiograms using Markov random fields. Digit Signal Process, 2010, 20(1): 149-154.
10.	Lu Y, Simonett J M, Wang J, et al. Evaluation of automatically quantified foveal avascular zone metrics for diagnosis of diabetic retinopathy using optical coherence tomography angiography. Invest Ophthalmol Vis Sci, 2018, 59(6): 2212-2221.
11.	Silva A G, Fouto M S, da Silva A T, et al. Segmentation of foveal avascular zone of the retina based on morphological alternating sequential filtering// 2015 IEEE 28th International Symposium on Computer-Based Medical Systems. S?o Carlos: IEEE, 2015: 38-43.
12.	Cheng P, Lin L, Huang Y, et al. Prior guided fundus image quality enhancement via contrastive learning// 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). Nice: IEEE, 2021: 521-525.
13.	Lin L, Wu J, Cheng P, et al. BLU-GAN: bi-directional ConvLSTM U-Net with generative adversarial training for retinal vessel segmentation// BenchCouncil International Federated Intelligent Computing and Block Chain Conferences. Singapore: Springer, 2020: 3-13.
14.	Lin L, Wu J, Liu Y, et al. Unifying and personalizing weakly-supervised federated medical image segmentation via adaptive representation and aggregation// International Workshop on Machine Learning in Medical Imaging. Cham: Springer, 2023: 196-206.
15.	Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
16.	Oktay O, Schlemper J, Folgoc L L, et al. Attention U-net: learning where to look for the pancreas. arXiv, 2018: 1804.03999.
17.	Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. UNet++: a nested U-Net architecture for medical image segmentation// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer, 2018: 3-11.
18.	Shang H, Feng T, Han D, et al. Deep learning and radiomics for gastric cancer serosal invasion: automated segmentation and multi-machine learning from two centers. J Cancer Res Clin Oncol, 2025, 151(2): 60.
19.	Wang J, Zhang B, Wang Y, et al. CrossU-Net: dual-modality cross-attention U-Net for segmentation of precancerous lesions in gastric cancer. Comput Med Imaging Graph, 2024, 112: 102339.
20.	Cao H, Wang Y, Chen J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation// European Conference on Computer Vision (ECCV). Cham: Springer, 2022: 205-218.
21.	Li C, Qiang Y, Sultan R I, et al. FocalUNETR: a focal transformer for boundary-aware prostate segmentation using CT images// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2023: 592-602.
22.	Tang H, Chen Y, Wang T, et al. HTC-Net: a hybrid CNN-transformer framework for medical image segmentation. Biomed Signal Process Control, 2024, 88: 105605.
23.	Meng Yongan, Lan Hailei, Hu Yuqian, et al. Application of improved U-Net convolutional neural network for automatic quantification of the foveal avascular zone in diabetic macular ischemia. J Diabetes Res, 2022, 2022: 4612554.
24.	Li M, Chen Y, Ji Z, et al. Image projection network: 3D to 2D image segmentation in OCTA images. IEEE Trans Med Imaging, 2020, 39(11): 3343-3354.
25.	Li M, Wang Y, Ji Z, et al. Fast and robust fovea detection framework for OCT images based on foveal avascular zone segmentation. OSA Continuum, 2020, 3(3): 528-541.
26.	Lin L, Wang Z, Wu J, et al. BSDA-net: a boundary shape and distance aware joint learning framework for segmenting and classifying OCTA images// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2021: 65-75.
27.	Xu Q, Li M, Pan N, et al. Priors-guided convolutional neural network for 3D foveal avascular zone segmentation. Opt Express, 2022, 30(9): 14723-14736.
28.	Guo M, Zhao M, Cheong A M Y, et al. Can deep learning improve the automatic segmentation of deep foveal avascular zone in optical coherence tomography angiography? Biomed Signal Process Control, 2021, 66: 102456.
29.	Li W, Zhang H, Li F, et al. RPS-net: an effective retinal image projection segmentation network for retinal vessels and foveal avascular zone based on OCTA data. Med Phys, 2022, 49(6): 3830-3844.
30.	Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation// European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 801-818.
31.	Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv, 2015: 1511.07122.
32.	Lau K W, Po L M, Rehman Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN. Expert Syst Appl, 2024, 236: 121352.
33.	Wang Z, Ji S. Smoothed dilated convolutions for improved dense prediction// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London: ACM, 2018: 2486-2495.
34.	Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation// 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe: IEEE, 2018: 1451-1460.
35.	Li M, Huang K, Xu Q, et al. OCTA-500: a retinal dataset for optical coherence tomography angiography study. Med Image Anal, 2024, 93: 103092.
36.	Arpit Agarwal, Jothi Balaji J, Rajiv Raman, and et al. The Foveal Avascular Zone Image Database (FAZID)// Applications of Digital Image Processing XLIII. SPIE, 2020, 11510: 507-512.
37.	Xiao Z, Du M, Liu J, et al. EA-UNet based segmentation method for OCT image of uterine cavity// Photonics. MDPI, 2023, 10(1): 73.
38.	Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12): 2481-2495.
39.	Huang H, Lin L, Tong R, et al. UNet 3+: a full-scale connected UNet for medical image segmentation// ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: IEEE, 2020: 1055-1059.
40.	Zhu C, Yang Z, Xiao Y, et al. TSCNet: transformer and snake convolution feature attention network for OCTA vessel segmentation. IEEE Trans Comput Soc Syst, 2025: 1-11.

1. Ang M, Tan A C S, Cheung C M G, et al. Optical coherence tomography angiography: a review of current and future clinical applications. Graefes Arch Clin Exp Ophthalmol, 2018, 256(2): 237-245.
2. Spaide R F, Fujimoto J G, Waheed N K, et al. Optical coherence tomography angiography. Prog Retin Eye Res, 2018, 64: 1-55.
3. Abramoff M D, Garvin M K, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng, 2010, 3: 169-208.
4. Salles M C, Kvanta A, Amrén U, et al. Optical coherence tomography angiography in central retinal vein occlusion: correlation between the foveal avascular zone and visual acuity. Invest Ophthalmol Vis Sci, 2016, 57(9): 242-246.
5. Linderman R, Salmon A E, Strampe M, et al. Assessing the accuracy of foveal avascular zone measurements using optical coherence tomography angiography: segmentation and scaling. Transl Vis Sci Technol, 2017, 6(3): 16.
6. Zheng Y, Gandhi J S, Stangos A N, et al. Automated segmentation of foveal avascular zone in fundus fluorescein angiography. Invest Ophthalmol Vis Sci, 2010, 51(7): 3653-3659.
7. Cheng K K W, Tan B L, Brown L, et al. Macular vessel density, branching complexity and foveal avascular zone size in normal tension glaucoma. Sci Rep, 2021, 11(1): 1056.
8. Jain K, Pegu J, Bhoot M, et al. Optical coherence tomography angiography of optic disc and macula vessel density in glaucoma and healthy eyes. J Glaucoma, 2019, 28(7): 131-132.
9. Haddouche A, Adel M, Rasigni M, et al. Detection of the foveal avascular zone on retinal angiograms using Markov random fields. Digit Signal Process, 2010, 20(1): 149-154.
10. Lu Y, Simonett J M, Wang J, et al. Evaluation of automatically quantified foveal avascular zone metrics for diagnosis of diabetic retinopathy using optical coherence tomography angiography. Invest Ophthalmol Vis Sci, 2018, 59(6): 2212-2221.
11. Silva A G, Fouto M S, da Silva A T, et al. Segmentation of foveal avascular zone of the retina based on morphological alternating sequential filtering// 2015 IEEE 28th International Symposium on Computer-Based Medical Systems. S?o Carlos: IEEE, 2015: 38-43.
12. Cheng P, Lin L, Huang Y, et al. Prior guided fundus image quality enhancement via contrastive learning// 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). Nice: IEEE, 2021: 521-525.
13. Lin L, Wu J, Cheng P, et al. BLU-GAN: bi-directional ConvLSTM U-Net with generative adversarial training for retinal vessel segmentation// BenchCouncil International Federated Intelligent Computing and Block Chain Conferences. Singapore: Springer, 2020: 3-13.
14. Lin L, Wu J, Liu Y, et al. Unifying and personalizing weakly-supervised federated medical image segmentation via adaptive representation and aggregation// International Workshop on Machine Learning in Medical Imaging. Cham: Springer, 2023: 196-206.
15. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
16. Oktay O, Schlemper J, Folgoc L L, et al. Attention U-net: learning where to look for the pancreas. arXiv, 2018: 1804.03999.
17. Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. UNet++: a nested U-Net architecture for medical image segmentation// Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer, 2018: 3-11.
18. Shang H, Feng T, Han D, et al. Deep learning and radiomics for gastric cancer serosal invasion: automated segmentation and multi-machine learning from two centers. J Cancer Res Clin Oncol, 2025, 151(2): 60.
19. Wang J, Zhang B, Wang Y, et al. CrossU-Net: dual-modality cross-attention U-Net for segmentation of precancerous lesions in gastric cancer. Comput Med Imaging Graph, 2024, 112: 102339.
20. Cao H, Wang Y, Chen J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation// European Conference on Computer Vision (ECCV). Cham: Springer, 2022: 205-218.
21. Li C, Qiang Y, Sultan R I, et al. FocalUNETR: a focal transformer for boundary-aware prostate segmentation using CT images// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2023: 592-602.
22. Tang H, Chen Y, Wang T, et al. HTC-Net: a hybrid CNN-transformer framework for medical image segmentation. Biomed Signal Process Control, 2024, 88: 105605.
23. Meng Yongan, Lan Hailei, Hu Yuqian, et al. Application of improved U-Net convolutional neural network for automatic quantification of the foveal avascular zone in diabetic macular ischemia. J Diabetes Res, 2022, 2022: 4612554.
24. Li M, Chen Y, Ji Z, et al. Image projection network: 3D to 2D image segmentation in OCTA images. IEEE Trans Med Imaging, 2020, 39(11): 3343-3354.
25. Li M, Wang Y, Ji Z, et al. Fast and robust fovea detection framework for OCT images based on foveal avascular zone segmentation. OSA Continuum, 2020, 3(3): 528-541.
26. Lin L, Wang Z, Wu J, et al. BSDA-net: a boundary shape and distance aware joint learning framework for segmenting and classifying OCTA images// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2021: 65-75.
27. Xu Q, Li M, Pan N, et al. Priors-guided convolutional neural network for 3D foveal avascular zone segmentation. Opt Express, 2022, 30(9): 14723-14736.
28. Guo M, Zhao M, Cheong A M Y, et al. Can deep learning improve the automatic segmentation of deep foveal avascular zone in optical coherence tomography angiography? Biomed Signal Process Control, 2021, 66: 102456.
29. Li W, Zhang H, Li F, et al. RPS-net: an effective retinal image projection segmentation network for retinal vessels and foveal avascular zone based on OCTA data. Med Phys, 2022, 49(6): 3830-3844.
30. Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation// European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 801-818.
31. Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv, 2015: 1511.07122.
32. Lau K W, Po L M, Rehman Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN. Expert Syst Appl, 2024, 236: 121352.
33. Wang Z, Ji S. Smoothed dilated convolutions for improved dense prediction// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London: ACM, 2018: 2486-2495.
34. Wang P, Chen P, Yuan Y, et al. Understanding convolution for semantic segmentation// 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe: IEEE, 2018: 1451-1460.
35. Li M, Huang K, Xu Q, et al. OCTA-500: a retinal dataset for optical coherence tomography angiography study. Med Image Anal, 2024, 93: 103092.
36. Arpit Agarwal, Jothi Balaji J, Rajiv Raman, and et al. The Foveal Avascular Zone Image Database (FAZID)// Applications of Digital Image Processing XLIII. SPIE, 2020, 11510: 507-512.
37. Xiao Z, Du M, Liu J, et al. EA-UNet based segmentation method for OCT image of uterine cavity// Photonics. MDPI, 2023, 10(1): 73.
38. Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017, 39(12): 2481-2495.
39. Huang H, Lin L, Tong R, et al. UNet 3+: a full-scale connected UNet for medical image segmentation// ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: IEEE, 2020: 1055-1059.
40. Zhu C, Yang Z, Xiao Y, et al. TSCNet: transformer and snake convolution feature attention network for OCTA vessel segmentation. IEEE Trans Comput Soc Syst, 2025: 1-11.

Journal of Biomedical Engineering

Optical coherence tomography angiography image segmentation based on multi-scale dilated convolution and dual attention network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content