Small-scale cross-layer fusion network for classification of diabetic retinopathy_Journal of Biomedical Engineering

Authors：

 GUO Ying , LI Shaojie

School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, P. R. China;

Corresponding author：

GUO Ying, Email: gy20072009@163.com

Keywords：

Small-scale convolution; Attention mechanism; Cross-layer fusion; Diabetic retinopathy

DOI：

10.7507/1001-5515.202403016

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Deep learning-based automatic classification of diabetic retinopathy (DR) helps to enhance the accuracy and efficiency of auxiliary diagnosis. This paper presents an improved residual network model for classifying DR into five different severity levels. First, the convolution in the first layer of the residual network was replaced with three smaller convolutions to reduce the computational load of the network. Second, to address the issue of inaccurate classification due to minimal differences between different severity levels, a mixed attention mechanism was introduced to make the model focus more on the crucial features of the lesions. Finally, to better extract the morphological features of the lesions in DR images, cross-layer fusion convolutions were used instead of the conventional residual structure. To validate the effectiveness of the improved model, it was applied to the Kaggle Blindness Detection competition dataset APTOS2019. The experimental results demonstrated that the proposed model achieved a classification accuracy of 97.75% and a Kappa value of 0.971 7 for the five DR severity levels. Compared to some existing models, this approach shows significant advantages in classification accuracy and performance.

Citation： GUO Ying, LI Shaojie. Small-scale cross-layer fusion network for classification of diabetic retinopathy. Journal of Biomedical Engineering, 2024, 41(5): 861-868. doi: 10.7507/1001-5515.202403016 Copy

1.	The International Diabetes Federation. New estimates indicate that more than 1.3 billion people could be living with diabetes by 2050. (2023-06-26) [2024-03-07]. https://idf.org/news/gbd-estimates-2021/.
2.	张惠蓉, 夏英杰. 视网膜静脉阻塞患者视力预后相关因素分析. 中华眼科杂志, 2002, 38(2): 37-41.
3.	Priya R, Aruna P. Diagnosis of diabetic retinopathy using machine learning techniques. J Soft Comput, 2013(4): 563-575.
4.	Lachure J, Deorankar A V, Lachure S, et al. Diabetic retinopathy using morphological operations and machine learning// 2015 IEEE International Advance Computing Conference (IACC). Banglore: IEEE, 2015: 617-622.
5.	Mohammadian S, Karsaz A, Roshan Y M. A comparative analysis of classification algorithms in diabetic retinopathy screening// 2017 International Conference on Computer and Knowledge Engineering (ICCKE). SiChuan: IEEE, 2017: 84-89.
6.	蔡轶珩, 高旭蓉, 邱长炎, 等. 一种混合特征高效融合的视网膜血管分割方法. 电子与信息学报, 2017, 39(8): 1956-1963.
7.	Farag M M, Fouad M, Abdel-Hamid A T. Automatic severity classification of diabetic retinopathy based on DenseNet and convolutional block attention module. IEEE Access, 2022, 10(3): 38299-38308.
8.	Gangwar A K, Ravi V. Diabetic retinopathy detection using transfer learning and deep learning// Evolution in Computational Intelligence: 2021 Frontiers in Intelligent Computing: Theory and Applications (FICTA). Singapore: Springer, 2021: 679-689.
9.	Khan Z, Khan F G, Khan A, et al. Diabetic retinopathy detection using VGG-NIN a deep learning architecture. IEEE Access, 2021, 9(3): 61408-61416.
10.	Kalyani G, Janakiramaiah B, Karuna A, et al. Diabetic retinopathy detection and classification using capsule networks. Complex Intell Syst, 2023, 9: 2651-2664.
11.	Huang K Q, Wang Q, Wu Z Y. Natural color image enhancement and evaluation algorithm based on human visual system. Comput Vis Image Und, 2006, 103(1): 52-63.
12.	Graham B. Kaggle diabetic retinopathy detection competition report. (2015-8-16) [2024-03-07]. https://www.kaggle.com/c/ diabetic-retinopathy-detection.
13.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition// 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
14.	Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module// 2018 Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3-19.
15.	Si Z, Fu D, Liu Y, et al. Hard exudate segmentation in retinal image with attention mechanism. IET Image Processing, 2021, 15(3): 587-597.
16.	Gao S H, Cheng M M, Zhao K, et al. Res2Net: A new multi-sclae backbone architecture. IEEE Trans Pattern Anal Mach Intell, 2019, 43(2): 652-662.
17.	Asia Pacific Tele-Ophthalmology Society. APTOS 2019 blindness detection. (2019-6-29) [2024-03-07]. https://www.kaggle.com/c/aptos2019-blindness-detection/overview.
18.	Wu L, Fernandez-Loaiza P, Sauma J, et al. Classification of diabetic retinopathy and diabetic macular edema. World J Diabetes, 2013, 4(6): 290-294.
19.	Ma X, Guo J, Chen Q, et al. Attention meets normalization and beyond// 2020 IEEE International Conference on Multimedia and Expo (ICME). London: IEEE, 2020: 1-6.
20.	Hu J, Shen L, Sun G. Squeeze-and-excitation networks// 2018 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
21.	Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks// 2020 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11534-11542.
22.	Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition// 1998 IEEE International Conference on Acoustics Speech and Signal Processing. Seattle: IEEE, 1998: 2278-2324.
23.	Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks// 2017 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 4700-4708.
24.	Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions// 2015 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Massachusetts: IEEE, 2015: 1-9.
25.	Haque A, Sutradhar I, Rahman M, et al. Convolutional nets for diabetic retinopathy screening in Bangladeshi patients. ArXiv e-prints, 2021, 21(8): 1-8.
26.	郑雯, 沈琪浩, 任佳. 基于Improved DR-Net算法的糖尿病视网膜病变识别与分级. 光学学报, 2021, 41(22): 72-83.
27.	Lu Z, Miao J, Dong J, et al. Automatic multilabel classification of multiple fundus diseases based on convolutional neural network with squeeze-and-excitation attention. Transl Vis Sci Technol, 2023, 12(1): 22-30.

1. The International Diabetes Federation. New estimates indicate that more than 1.3 billion people could be living with diabetes by 2050. (2023-06-26) [2024-03-07]. https://idf.org/news/gbd-estimates-2021/.
2. 张惠蓉, 夏英杰. 视网膜静脉阻塞患者视力预后相关因素分析. 中华眼科杂志, 2002, 38(2): 37-41.
3. Priya R, Aruna P. Diagnosis of diabetic retinopathy using machine learning techniques. J Soft Comput, 2013(4): 563-575.
4. Lachure J, Deorankar A V, Lachure S, et al. Diabetic retinopathy using morphological operations and machine learning// 2015 IEEE International Advance Computing Conference (IACC). Banglore: IEEE, 2015: 617-622.
5. Mohammadian S, Karsaz A, Roshan Y M. A comparative analysis of classification algorithms in diabetic retinopathy screening// 2017 International Conference on Computer and Knowledge Engineering (ICCKE). SiChuan: IEEE, 2017: 84-89.
6. 蔡轶珩, 高旭蓉, 邱长炎, 等. 一种混合特征高效融合的视网膜血管分割方法. 电子与信息学报, 2017, 39(8): 1956-1963.
7. Farag M M, Fouad M, Abdel-Hamid A T. Automatic severity classification of diabetic retinopathy based on DenseNet and convolutional block attention module. IEEE Access, 2022, 10(3): 38299-38308.
8. Gangwar A K, Ravi V. Diabetic retinopathy detection using transfer learning and deep learning// Evolution in Computational Intelligence: 2021 Frontiers in Intelligent Computing: Theory and Applications (FICTA). Singapore: Springer, 2021: 679-689.
9. Khan Z, Khan F G, Khan A, et al. Diabetic retinopathy detection using VGG-NIN a deep learning architecture. IEEE Access, 2021, 9(3): 61408-61416.
10. Kalyani G, Janakiramaiah B, Karuna A, et al. Diabetic retinopathy detection and classification using capsule networks. Complex Intell Syst, 2023, 9: 2651-2664.
11. Huang K Q, Wang Q, Wu Z Y. Natural color image enhancement and evaluation algorithm based on human visual system. Comput Vis Image Und, 2006, 103(1): 52-63.
12. Graham B. Kaggle diabetic retinopathy detection competition report. (2015-8-16) [2024-03-07]. https://www.kaggle.com/c/ diabetic-retinopathy-detection.
13. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition// 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
14. Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module// 2018 Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3-19.
15. Si Z, Fu D, Liu Y, et al. Hard exudate segmentation in retinal image with attention mechanism. IET Image Processing, 2021, 15(3): 587-597.
16. Gao S H, Cheng M M, Zhao K, et al. Res2Net: A new multi-sclae backbone architecture. IEEE Trans Pattern Anal Mach Intell, 2019, 43(2): 652-662.
17. Asia Pacific Tele-Ophthalmology Society. APTOS 2019 blindness detection. (2019-6-29) [2024-03-07]. https://www.kaggle.com/c/aptos2019-blindness-detection/overview.
18. Wu L, Fernandez-Loaiza P, Sauma J, et al. Classification of diabetic retinopathy and diabetic macular edema. World J Diabetes, 2013, 4(6): 290-294.
19. Ma X, Guo J, Chen Q, et al. Attention meets normalization and beyond// 2020 IEEE International Conference on Multimedia and Expo (ICME). London: IEEE, 2020: 1-6.
20. Hu J, Shen L, Sun G. Squeeze-and-excitation networks// 2018 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
21. Wang Q, Wu B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks// 2020 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11534-11542.
22. Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition// 1998 IEEE International Conference on Acoustics Speech and Signal Processing. Seattle: IEEE, 1998: 2278-2324.
23. Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks// 2017 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 4700-4708.
24. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions// 2015 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Massachusetts: IEEE, 2015: 1-9.
25. Haque A, Sutradhar I, Rahman M, et al. Convolutional nets for diabetic retinopathy screening in Bangladeshi patients. ArXiv e-prints, 2021, 21(8): 1-8.
26. 郑雯, 沈琪浩, 任佳. 基于Improved DR-Net算法的糖尿病视网膜病变识别与分级. 光学学报, 2021, 41(22): 72-83.
27. Lu Z, Miao J, Dong J, et al. Automatic multilabel classification of multiple fundus diseases based on convolutional neural network with squeeze-and-excitation attention. Transl Vis Sci Technol, 2023, 12(1): 22-30.

Previous Article
Advances in the diagnosis of prostate cancer based on image fusion
Next Article
Research and implementation of intelligent diagnostic system for temporomandibular joint disorder

Journal of Biomedical Engineering

Small-scale cross-layer fusion network for classification of diabetic retinopathy

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content