An adaptive multi-label classification model for diabetic retinopathy lesion recognition_Journal of Biomedical Engineering

Authors：

LIU Xina ¹ ,  XIE Jun ² ,  HOU Junjun ³ , XU Xinying ¹ , GUO Yan ⁴

1. College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan Shanxi 030024, P. R. China;
2. College of Electronic Information and Optical Engineering, Taiyuan University of Technology, Jinzhong, Shanxi 030600, P. R. China;
3. Shanxi Eye Hospital, Taiyuan 030002, P. R. China;
4. The Third Affiliated Hospital of Beijing University of Chinese Medicine, Beijing 100084, P. R. China;

Corresponding?author：

XIE Jun, Email: xiejun@tyut.edu.cn; HOU Junjun, Email: junjunhou@126.com

Keywords：

Diabetic retinopathy; Fundus fluorescein angiography; Lesion recognition; Multi-label classification; Category-adaptive mapping; Label-specific decoding; Smooth focal loss

DOI：

10.7507/1001-5515.202503056

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Diabetic retinopathy is a common blinding complication in diabetic patients. Compared with conventional fundus color photography, fundus fluorescein angiography can dynamically display retinal vessel permeability changes, offering unique advantages in detecting early small lesions such as microaneurysms. However, existing intelligent diagnostic research on diabetic retinopathy images primarily focuses on fundus color photography, with relatively insufficient research on complex lesion recognition in fluorescein angiography images. This study proposed an adaptive multi-label classification model (D-LAM) to improve the recognition accuracy of small lesions by constructing a category-adaptive mapping module, a label-specific decoding module, and an innovative loss function. Experimental results on a self-built dataset demonstrated that the model achieved a mean average precision of 96.27%, a category F1-score of 91.21%, and an overall F1-score of 94.58%, with particularly outstanding performance in recognizing small lesions such as microaneurysms (AP = 1.00), significantly outperforming existing methods. The research provides reliable technical support for clinical diagnosis of diabetic retinopathy based on fluorescein angiography.

1.	Wang W, Lo A C Y. Diabetic retinopathy: pathophysiology and treatments. Int J Mol Sci, 2018, 19(6): 1816.
2.	Gerendas B S, Bogunovic H, Sadeghipour A, et al. Computational image analysis for prognosis determination in DME. Vision Res, 2017, 139: 204-210.
3.	Deka A, Sarma K K. SVD and PCA features for ANN based detection of diabetes using retinopathy// Proceedings of the CUBE International Information Technology Conference. New York: Association for Computing Machinery, 2012: 38-41.
4.	Roychowdhury S, Koozekanani D D, Parhi K K. DREAM: Diabetic retinopathy analysis using machine learning. IEEE J Biomed Health Inform, 2014, 18(5): 1717-1728.
5.	Sun G, Liu X, Yu X. Multi-path cascaded U-net for vessel segmentation from fundus fluorescein angiography sequential images. Comput Methods Programs Biomed, 2021, 211: 106422.
6.	Chen M, Jin K, You K, et al. Automatic detection of leakage point in central serous chorioretinopathy of fundus fluorescein angiography based on time sequence deep learning. Graefes Arch Clin Exp Ophthalmol, 2021, 259(8): 2401-2411.
7.	Gao Z, Jin K, Yan Y, et al. End-to-end diabetic retinopathy grading based on fundus fluorescein angiography images using deep learning. Graefes Arch Clin Exp Ophthalmol, 2022, 260(5): 1663-1673.
8.	Chen Z M, Wei X S, Wang P, et al. Multi-label image recognition with graph convolutional networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2019: 5177-5186.
9.	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation// Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer, 2015: 234-241.
10.	Wang S, Zuo Y, Wang N, et al. Fundus fluorescence angiography in diagnosing diabetic retinopathy. Pak J Med Sci, 2017, 33(6): 1328.
11.	Liu X, Xie J, Hou J, et al. D-GET: group-enhanced transformer for diabetic retinopathy severity classification in fundus fluorescein angiography. J Med Syst, 2025, 49(1): 34.
12.	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2016: 2818-2826.
13.	Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection// Proceedings of the IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society, 2017: 2980-2988.
14.	LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
15.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2016: 770-778.
16.	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv, 2015: 1409.1556.
17.	Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2017: 4700-4708.
18.	Tan M, Pang R, Le Q V. EfficientDet: scalable and efficient object detection// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2020: 10781-10790.
19.	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. Los Alamitos: IEEE Computer Society, 2021: 10012-10022.
20.	Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv, 2020: 2010.11929.
21.	Qiu Z, Hu Y, Chen X, et al. Rethinking dual-stream super-resolution semantic learning in medical image segmentation. IEEE Trans Pattern Anal Mach Intell, 2024, 46(1): 451-464.
22.	Zhu K, Wu J. Residual attention: a simple but effective method for multi-label recognition// Proceedings of the IEEE/CVF International Conference on Computer Vision. Los Alamitos: IEEE Computer Society, 2021: 184-193.
23.	Lanchantin J, Wang T, Ordonez V, et al. General multi-label image classification with transformers// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2021: 16478-16488.
24.	He A, Wang K, Li T, et al. H2Former: an efficient hierarchical hybrid transformer for medical image segmentation. IEEE Trans Med Imaging, 2023, 42(9): 2763-2775.
25.	Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2020: 11534-11542.
26.	Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 3-19.

1. Wang W, Lo A C Y. Diabetic retinopathy: pathophysiology and treatments. Int J Mol Sci, 2018, 19(6): 1816.
2. Gerendas B S, Bogunovic H, Sadeghipour A, et al. Computational image analysis for prognosis determination in DME. Vision Res, 2017, 139: 204-210.
3. Deka A, Sarma K K. SVD and PCA features for ANN based detection of diabetes using retinopathy// Proceedings of the CUBE International Information Technology Conference. New York: Association for Computing Machinery, 2012: 38-41.
4. Roychowdhury S, Koozekanani D D, Parhi K K. DREAM: Diabetic retinopathy analysis using machine learning. IEEE J Biomed Health Inform, 2014, 18(5): 1717-1728.
5. Sun G, Liu X, Yu X. Multi-path cascaded U-net for vessel segmentation from fundus fluorescein angiography sequential images. Comput Methods Programs Biomed, 2021, 211: 106422.
6. Chen M, Jin K, You K, et al. Automatic detection of leakage point in central serous chorioretinopathy of fundus fluorescein angiography based on time sequence deep learning. Graefes Arch Clin Exp Ophthalmol, 2021, 259(8): 2401-2411.
7. Gao Z, Jin K, Yan Y, et al. End-to-end diabetic retinopathy grading based on fundus fluorescein angiography images using deep learning. Graefes Arch Clin Exp Ophthalmol, 2022, 260(5): 1663-1673.
8. Chen Z M, Wei X S, Wang P, et al. Multi-label image recognition with graph convolutional networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2019: 5177-5186.
9. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation// Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer, 2015: 234-241.
10. Wang S, Zuo Y, Wang N, et al. Fundus fluorescence angiography in diagnosing diabetic retinopathy. Pak J Med Sci, 2017, 33(6): 1328.
11. Liu X, Xie J, Hou J, et al. D-GET: group-enhanced transformer for diabetic retinopathy severity classification in fundus fluorescein angiography. J Med Syst, 2025, 49(1): 34.
12. Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2016: 2818-2826.
13. Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection// Proceedings of the IEEE International Conference on Computer Vision. Los Alamitos: IEEE Computer Society, 2017: 2980-2988.
14. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
15. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2016: 770-778.
16. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv, 2015: 1409.1556.
17. Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2017: 4700-4708.
18. Tan M, Pang R, Le Q V. EfficientDet: scalable and efficient object detection// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2020: 10781-10790.
19. 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. Los Alamitos: IEEE Computer Society, 2021: 10012-10022.
20. Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv, 2020: 2010.11929.
21. Qiu Z, Hu Y, Chen X, et al. Rethinking dual-stream super-resolution semantic learning in medical image segmentation. IEEE Trans Pattern Anal Mach Intell, 2024, 46(1): 451-464.
22. Zhu K, Wu J. Residual attention: a simple but effective method for multi-label recognition// Proceedings of the IEEE/CVF International Conference on Computer Vision. Los Alamitos: IEEE Computer Society, 2021: 184-193.
23. Lanchantin J, Wang T, Ordonez V, et al. General multi-label image classification with transformers// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2021: 16478-16488.
24. He A, Wang K, Li T, et al. H2Former: an efficient hierarchical hybrid transformer for medical image segmentation. IEEE Trans Med Imaging, 2023, 42(9): 2763-2775.
25. Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society, 2020: 11534-11542.
26. Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 3-19.

Journal of Biomedical Engineering

Latest ArticlesAn adaptive multi-label classification model for diabetic retinopathy lesion recognition

Abstract Full text Figures/Tables Video References Cited by

Format

Content