Research on attention-enhanced networks for subtype classification of age-related macular degeneration in optical coherence tomography_Journal of Biomedical Engineering

Authors：

 CHEN Minghui ¹ , YANG Wenyi ¹ , XU Shiyi ¹ , LU Yanqi ¹ , YANG Zhengqi ¹ , LI Fugang ² , GU Zhensheng ³

1. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China;
2. Shanghai Upper Bio-Tech Pharma Co., LTD, Shanghai 200003, P. R. China;
3. Department of Ophthalmology, Xin Hua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200092, P. R. China;

Corresponding author：

CHEN Minghui, Email: cmhui.43@163.com

Keywords：

Optical coherence tomography; Age-related macular degeneration; Image classification; Key point location; Two-dimensional relative self-attention mechanism

DOI：

10.7507/1001-5515.202408029

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Subtype classification of age-related macular degeneration (AMD) based on optical coherence tomography (OCT) images serves as an effective auxiliary tool for clinicians in diagnosing disease progression and formulating treatment plans. To improve the classification accuracy of AMD subtypes, this study proposes a keypoint-based, attention-enhanced residual network (KPA-ResNet). The proposed architecture adopts a 50-layer residual network (ResNet-50) as the backbone, preceded by a keypoint localization module based on heatmap regression to outline critical lesion regions. A two-dimensional relative self-attention mechanism is incorporated into convolutional layers to enhance the representation of key lesion areas. Furthermore, the network depth is appropriately increased and an improved residual module, ConvNeXt, is introduced to enable comprehensive extraction of high-dimensional features and enrich the detail of lesion boundary contours, ultimately achieving higher classification accuracy of AMD subtypes. Experimental results demonstrate that KPA-ResNet achieves significant improvements in overall classification accuracy compared with conventional convolutional neural networks. Specifically, for the wet AMD subtypes, the classification accuracies for inactive choroidal neovascularization (CNV) and active CNV reach 92.8% and 95.2%, respectively, representing substantial improvement over ResNet-50. These findings validate the superior performance of KPA-ResNet in AMD subtype classification tasks. This work provides a high-accuracy, generalizable network architecture for OCT-based AMD subtype classification and offers new insights into integrating attention mechanisms with convolutional neural networks in ophthalmic image analysis.

Citation： CHEN Minghui, YANG Wenyi, XU Shiyi, LU Yanqi, YANG Zhengqi, LI Fugang, GU Zhensheng. Research on attention-enhanced networks for subtype classification of age-related macular degeneration in optical coherence tomography. Journal of Biomedical Engineering, 2025, 42(5): 901-909. doi: 10.7507/1001-5515.202408029 Copy

1.	Tsang J Y, Wright A, Carr M J, et al. Risk of falls and fractures in individuals with cataract, age-related macular degeneration, or glaucoma. JAMA Ophthalmol, 2024, 142(2): 96-106.
2.	Miotto S, Zemella N, Gusson E, et al. Morphologic criteria of lesion activity in neovascular age-related macular degeneration: a consensus article. Journal of Ocular Pharmacology and Therapeutics, 2018, 34(3): 298-308.
3.	邵毅, 温佳怡, 令倩. 年龄相关性黄斑变性诊断与治疗规范: 2022年英国皇家眼科医学会指南解读. 眼科新进展, 2023, 43(2): 85-88.
4.	Bakri S J, Thorne J E, Ho A C, et al. Safety and efficacy of anti-vascular endothelial growth factor therapies for neovascular age-related macular degeneration: a report by the American Academy of Ophthalmology. Ophthalmology, 2019, 126(1): 55-63.
5.	Deng Y, Qiao L, Du M, et al. Age-related macular degeneration: epidemiology, genetics, pathophysiology, diagnosis, and targeted therapy. Genes Dis, 2021, 9(1): 62-79.
6.	Wang J, He Y, Fang W, et al. Unsupervised domain adaptation model for lesion detection in retinal OCT images. Phys Med Biol, 2021, 66: 215006.
7.	Lupidi M, Cerquaglia A, Chhablani J, et al. Optical coherence tomography angiography in age-related macular degeneration: the game changer. Eur J Ophthalmol, 2018, 28(4): 349-357.
8.	Wang J, Li W, Chen Y, et al. Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach. Biomedical Optics Express, 2021, 12(8): 4713-4729.
9.	汪荣贵, 姚旭晨, 杨娟, 等. 基于深度迁移学习的微型细粒度图像分类. 光电工程, 2019, 46(6): 26-35.
10.	齐永锋, 吕雪超, 裴晓旭, 等. 基于生成对抗网络的高光谱图像分类. 光电子·激光, 2021, 32(12): 1285-1292.
11.	Lee C S, Baughman D M, Lee A Y. Deep learning is effective for the classification of OCT images of normal versus age-related macular degeneration. Ophthalmol Retina, 2017, 1(4): 322-327.
12.	Serener A, Serte S. Dry and wet age-related macular degeneration classification using oct images and deep learning//2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), Istanbul: IEEE, 2019: 1-4.
13.	Wang W, Xu Z, Yu W, et al. Two-stream CNN with loose pair training for multi-modal AMD categorization//Medical Image Computing and Computer Assisted Intervention–MICCAI 2019, Shenzhen: Springer International Publishing, 2019: 156-164.
14.	Vaghefi E, Hill S, Kersten H M, et al. Multi-modal retinal image analysis via deep learning for the diagnosis of intermediate dry age-related macular degeneration: a feasibility study. Journal of Ophthalmology, 2020, 2020: 7493419.
15.	Xu Z, Wang W, Yang J, et al. Automated diagnoses of age-related macular degeneration and polypoidal choroidal vasculopathy using bi-modal deep convolutional neural networks. British Journal of Ophthalmology, 2021, 105(4): 561-566.
16.	Hwang D K, Hsu C C, Chang K J, et al. Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics, 2019, 9(1): 232-245.
17.	E Haihong, Ding J, Yuan L. SAE-wAMD: a self-attention enhanced convolution neural network for fine-grained classification of wet age-related macular degeneration using OCT image//2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), Xi’an: IEEE, 2023: 619-627.
18.	Ma Z, Xie Q, Xie P, et al. HCTNet: a hybrid ConvNet-Transformer network for retinal optical coherence tomography image classification. Biosensors, 2022, 12(7): 542.
19.	杨文逸, 陈明惠, 吴玉全, 等. 采用自注意力机制的OCT图像AMD亚型分类研究. 光学技术, 2024, 50(1): 112-119.
20.	许伟濠, 张伯泉, 刘银萍. 基于热力图和注意力机制的单目6D姿态估计算法. 微电子学与计算机, 2023, 40(7): 45-54.
21.	Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations. arXiv preprint, 2018, arXiv: 1803.02155.
22.	Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal: IEEE, 2021: 10012-10022.
23.	Hu J, Shen L, Sun G. Squeeze-and-excitation networks//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City: IEEE, 2018: 7132-7141.
24.	Hu J, Shen L, Albanie S, et al. Gather-excite: exploiting feature context in convolutional neural networks//32nd Conference on Neural Information Processing Systems (NIPS 2018), Montréal: NIPS, 2018, 31: 1-11.
25.	Park J, Woo S, Lee J Y, et al. BAM: bottleneck attention module. arXiv preprint, 2018, arXiv: 1807.06514.
26.	Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module//Proceedings of the European Conference on Computer Vision (ECCV), Munich: IEEE, 2018: 3-19.
27.	Zhang H, Yang S, Zhang X. Automatic recognition and classification of microalgae using an inception-v3 convolution neural network model. International Journal of Environmental Science and Technology, 2023, 21(4): 4625-4634.
28.	Anand R, Lakshmi V S, Pandey B K. An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators. Evolving Systems, 2023, 15(1): 83-97.
29.	Saluja S, Trivedi M C, Sarangdevot S S. Advancing glioma diagnosis: Integrating custom U-Net and VGG-16 for improved grading in MR imaging. Math Biosci Eng, 2024, 21(3): 4328-4350.

1. Tsang J Y, Wright A, Carr M J, et al. Risk of falls and fractures in individuals with cataract, age-related macular degeneration, or glaucoma. JAMA Ophthalmol, 2024, 142(2): 96-106.
2. Miotto S, Zemella N, Gusson E, et al. Morphologic criteria of lesion activity in neovascular age-related macular degeneration: a consensus article. Journal of Ocular Pharmacology and Therapeutics, 2018, 34(3): 298-308.
3. 邵毅, 温佳怡, 令倩. 年龄相关性黄斑变性诊断与治疗规范: 2022年英国皇家眼科医学会指南解读. 眼科新进展, 2023, 43(2): 85-88.
4. Bakri S J, Thorne J E, Ho A C, et al. Safety and efficacy of anti-vascular endothelial growth factor therapies for neovascular age-related macular degeneration: a report by the American Academy of Ophthalmology. Ophthalmology, 2019, 126(1): 55-63.
5. Deng Y, Qiao L, Du M, et al. Age-related macular degeneration: epidemiology, genetics, pathophysiology, diagnosis, and targeted therapy. Genes Dis, 2021, 9(1): 62-79.
6. Wang J, He Y, Fang W, et al. Unsupervised domain adaptation model for lesion detection in retinal OCT images. Phys Med Biol, 2021, 66: 215006.
7. Lupidi M, Cerquaglia A, Chhablani J, et al. Optical coherence tomography angiography in age-related macular degeneration: the game changer. Eur J Ophthalmol, 2018, 28(4): 349-357.
8. Wang J, Li W, Chen Y, et al. Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach. Biomedical Optics Express, 2021, 12(8): 4713-4729.
9. 汪荣贵, 姚旭晨, 杨娟, 等. 基于深度迁移学习的微型细粒度图像分类. 光电工程, 2019, 46(6): 26-35.
10. 齐永锋, 吕雪超, 裴晓旭, 等. 基于生成对抗网络的高光谱图像分类. 光电子·激光, 2021, 32(12): 1285-1292.
11. Lee C S, Baughman D M, Lee A Y. Deep learning is effective for the classification of OCT images of normal versus age-related macular degeneration. Ophthalmol Retina, 2017, 1(4): 322-327.
12. Serener A, Serte S. Dry and wet age-related macular degeneration classification using oct images and deep learning//2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), Istanbul: IEEE, 2019: 1-4.
13. Wang W, Xu Z, Yu W, et al. Two-stream CNN with loose pair training for multi-modal AMD categorization//Medical Image Computing and Computer Assisted Intervention–MICCAI 2019, Shenzhen: Springer International Publishing, 2019: 156-164.
14. Vaghefi E, Hill S, Kersten H M, et al. Multi-modal retinal image analysis via deep learning for the diagnosis of intermediate dry age-related macular degeneration: a feasibility study. Journal of Ophthalmology, 2020, 2020: 7493419.
15. Xu Z, Wang W, Yang J, et al. Automated diagnoses of age-related macular degeneration and polypoidal choroidal vasculopathy using bi-modal deep convolutional neural networks. British Journal of Ophthalmology, 2021, 105(4): 561-566.
16. Hwang D K, Hsu C C, Chang K J, et al. Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics, 2019, 9(1): 232-245.
17. E Haihong, Ding J, Yuan L. SAE-wAMD: a self-attention enhanced convolution neural network for fine-grained classification of wet age-related macular degeneration using OCT image//2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), Xi’an: IEEE, 2023: 619-627.
18. Ma Z, Xie Q, Xie P, et al. HCTNet: a hybrid ConvNet-Transformer network for retinal optical coherence tomography image classification. Biosensors, 2022, 12(7): 542.
19. 杨文逸, 陈明惠, 吴玉全, 等. 采用自注意力机制的OCT图像AMD亚型分类研究. 光学技术, 2024, 50(1): 112-119.
20. 许伟濠, 张伯泉, 刘银萍. 基于热力图和注意力机制的单目6D姿态估计算法. 微电子学与计算机, 2023, 40(7): 45-54.
21. Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations. arXiv preprint, 2018, arXiv: 1803.02155.
22. Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal: IEEE, 2021: 10012-10022.
23. Hu J, Shen L, Sun G. Squeeze-and-excitation networks//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City: IEEE, 2018: 7132-7141.
24. Hu J, Shen L, Albanie S, et al. Gather-excite: exploiting feature context in convolutional neural networks//32nd Conference on Neural Information Processing Systems (NIPS 2018), Montréal: NIPS, 2018, 31: 1-11.
25. Park J, Woo S, Lee J Y, et al. BAM: bottleneck attention module. arXiv preprint, 2018, arXiv: 1807.06514.
26. Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module//Proceedings of the European Conference on Computer Vision (ECCV), Munich: IEEE, 2018: 3-19.
27. Zhang H, Yang S, Zhang X. Automatic recognition and classification of microalgae using an inception-v3 convolution neural network model. International Journal of Environmental Science and Technology, 2023, 21(4): 4625-4634.
28. Anand R, Lakshmi V S, Pandey B K. An enhanced ResNet-50 deep learning model for arrhythmia detection using electrocardiogram biomedical indicators. Evolving Systems, 2023, 15(1): 83-97.
29. Saluja S, Trivedi M C, Sarangdevot S S. Advancing glioma diagnosis: Integrating custom U-Net and VGG-16 for improved grading in MR imaging. Math Biosci Eng, 2024, 21(3): 4328-4350.

Journal of Biomedical Engineering

Research on attention-enhanced networks for subtype classification of age-related macular degeneration in optical coherence tomography

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content