Research on lightweight model of intelligent-assisted diagnosis of common fundus diseases based on fundus color photography_Chinese Journal of Ocular Fundus Diseases

Authors：

Lu Bing ^1,2 , Wu Maonian ^1,2 , Zheng Bo ^1,2 , Zhu Shaojun ^1,2 , Hao Xiulan ^1,2 , Chen Nan ³ , Hou Zejiang ³ , Jiang Qin ³ ,  Yang Weihua ³

1. School of Information Engineering, Huzhou University, Huzhou 313000, China;
2. Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou University, Hangzhou 313000, China;
3. Ophthalmology Artificial Intelligence Big Data Laboratory, Affiliated Eye Hospital of Nanjing Medical University, Nanjing 210029, China;

Corresponding author：

Yang Weihua, Email: benben0606@139.com

Keywords：

Retinal diseases; Artificial intelligence; Diagnosis, computer-assisted; Lightweight model

DOI：

10.3760/cma.j.cn511434-20210618-00327

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To observe the diagnostic value of six classification intelligent auxiliary diagnosis lightweight model for common fundus diseases based on fundus color photography. Methods A applied research. A dataset of 2 400 color fundus images from Nanjing Medical University Eye Hospital and Zhejiang Mathematical Medical Society Smart Eye Database was collected, which was desensitized and labeled by a fundus specialist. Of these, 400 each were for diabetic retinopathy, glaucoma, retinal vein occlusion, high myopia, age-related macular degeneration, and normal fundus. The parameters obtained from the classical classification models VGGNet16, ResNet50, DenseNet121 and lightweight classification models MobileNet3, ShuffleNet2, GhostNet trained on the ImageNet dataset were migrated to the six-classified common fundus disease intelligent aid diagnostic model using a migration learning approach during training as initialization parameters for training to obtain the latest model. 1 315 color fundus images of clinical patients were used as the test set. Evaluation metrics included sensitivity, specificity, accuracy, F1-Score and agreement of diagnostic tests (Kappa value); comparison of subject working characteristic curves as well as area under the curve values for different models. Result Compared with the classical classification model, the storage size and number of parameters of the three lightweight classification models were significantly reduced, with ShuffleNetV2 having an average recognition time per sheet 438.08 ms faster than the classical classification model VGGNet16. All 3 lightweight classification models had Accuracy > 80.0%; Kappa values > 70.0% with significant agreement; sensitivity, specificity, and F1-Score for the diagnosis of normal fundus images were ≥ 98.0%; Macro-F1 was 78.2%, 79.4%, and 81.5%, respectively. Conclusion The intelligent assisted diagnosis of common fundus diseases based on fundus color photography is a lightweight model with high recognition accuracy and speed; the storage size and number of parameters are significantly reduced compared with the classical classification model.

Citation： Lu Bing, Wu Maonian, Zheng Bo, Zhu Shaojun, Hao Xiulan, Chen Nan, Hou Zejiang, Jiang Qin, Yang Weihua. Research on lightweight model of intelligent-assisted diagnosis of common fundus diseases based on fundus color photography. Chinese Journal of Ocular Fundus Diseases, 2022, 38(2): 146-152. doi: 10.3760/cma.j.cn511434-20210618-00327 Copy

1.	Walter T, Massin P, Erginay A, et al. Automatic detection of microaneurysms in color fundus images[J]. Med Image Anal, 2007, 11(6): 555-566. DOI: 10.1016/j.media.2007.05.001.
2.	邹海东, 何明光. 积极开展社区糖尿病视网膜病变筛查和早期干预工作[J]. 中华眼科杂志, 2016, 52(11): 801-804. DOI: 10.3760/cma.j.issn.0412-4081.2016.11.001.Zou HD, He MG. Active screening and early intervention of diabetic retinopathy in community service[J]. Chin J Ophthalmol, 2016, 52(11): 801-804. DOI: 10.3760/cma.j.issn.0412-4081.2016.11.001.
3.	Goldbaum MH, Sample PA, White H, et al. Interpretation of automated perimetry for glaucoma by neural network[J]. Invest Ophthalmol Vis Sci, 1994, 35(9): 3362-3373.
4.	LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI: 10.1038/nature14539.
5.	肖璐璐, 窦晓燕. 人工智能在眼部疾病中的应用及其挑战[J]. 国际眼科杂志, 2020, 20(7): 1197-1201. DOI: 10.3980/j.issn.1672-5123.2020.7.18.Xiao LL, Dou XY. Application of artificial Intelligence and deep learning in ophthalmology[J]. Int Eye Sci, 2020, 20(7): 1197-1201. DOI: 10.3980/j.issn.1672-5123.2020.7.18.
6.	Elswah DK, Elnakib AA, Moustafa HE. Automated diabetic retinopathy grading using resnet[C]. 2020 37th National Radio Science Conference (NRSC). Cairo: IEEE, 2020: 248-254.
7.	Lee T, Jammal AA, Mariottoni EB, et al. Predicting glaucoma development with longitudinal deep learning predictions from fundus photographs[J]. Am J Ophthalmol, 2021, 225: 86-94. DOI: 10.1016/j.ajo.2020.12.031.
8.	Nagasato D, Tabuchi H, Ohsugi H, et al. Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion[J]. Int J Ophthalmol, 2019, 12(1): 94-99. DOI: 10.18240/ijo.2019.01.15.
9.	Tang Z, Zhang X, Yang G, et al. Automated segmentation of retinal nonperfusion area in fluorescein angiography in retinal vein occlusion using convolutional neural networks[J]. Medical Physics, 2021, 48(2): 648-658. DOI: 10.1002/mp.14640.
10.	Li Y, Feng W, Zhao X, et al. Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images[J/OL]. Br J Ophthalmol, 2020, bjophthalmol-2020-317825(2021-06-18)[2021-06-18]. https://bjo.bmj.com/content/bjophthalmol/early/2020/12/20/bjophthalmol-2020-317825.full.pdf. DOI: 10.1136/bjophthalmol-2020-317825. [published online ahead of print].
11.	Yim J, Chopra R, Spitz T, et al. Predicting conversion to wet age-related macular degeneration using deep learning[J]. Nat Med, 2020, 26(6): 892-899. DOI: 10.1038/s41591-020-0867-7.
12.	Li Z, He Y, Keel S, et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs[J]. Ophthalmology, 2018, 125(8): 1199-1206. DOI: 10.1016/j.ophtha.2018.01.023.
13.	Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]. JAMA, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
14.	Iandola FN, Han S, Moskewicz MW, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5 MB model size[C]. International Conference on Learning Representations. Toulon: ICLR, 2017: 1-13.
15.	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 2818-2826.
16.	Pan SJ, Yang Q. A survey on transfer learning[J]. IEEE T Knowl Data En, 2009, 22(10): 1345-1359. DOI: 10.1109/TKDE.2009.191.
17.	Wilkinson CP, Ferris FL 3rd, Klein RE, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales[J]. Ophthalmology, 2003, 110(9): 1677-1682. DOI: 10.1016/S0161-6420(03)00475-5.
18.	Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul: ICCV, 2019: 1314-1324.
19.	Ma N, Zhang X, Zheng HT, et al. Shufflenet v2: practical guidelines for efficient cnn architecture design[C]. Proceedings of the European Conference on Computer Vision (ECCV). Munich: ECCV, 2018: 116-131.
20.	Han K, Wang Y, Tian Q, et al. Ghostnet: more features from cheap operations[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: CVPR, 2020: 1580-1589.
21.	Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems. Nevada: NIPS, 2012, 25: 1097-1105.
22.	Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C/OL]. International Conference on Learning Representations, San Diego, 2015[2015-05-07]. https://iclr.cc/archive/www/2015.html.
23.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 770-778.
24.	Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: CVPR, 2017: 4700-4708.
25.	丁喜艳, 杨卫华, 曹国凡, 等. 人工智能在青光眼诊断中的应用[J]. 中国数字医学, 2021, 16(2): 49-53. DOI: 10.3969/j.issn.1673-7571.2021.02.011.Ding XY, Yang WH, Cao GF, et al. Application of artificial intelligence in the diagnosis of glaucoma[J]. Application of New Technology, 2021, 16(2): 49-53. DOI: 10.3969/j.issn.1673-7571.2021.02.011.
26.	Cao K, Xu J, Zhao WQ. Artificial intelligence on diabetic retinopathy diagnosis: an automatic classification method based on grey level co-occurrence matrix and naive Bayesian model[J]. Int J Ophthalmol, 2019, 12(7): 1158. DOI: 10.18240/ijo.2019.07.17.
27.	Yang WH, Zheng B, Wu MN, et al. An evaluation system of fundus photograph-based intelligent diagnostic technology for diabetic retinopathy and applicability for research[J]. Diabetes Ther, 2019, 10(5): 1811-1822. DOI: 10.1007/s13300-019-0652-0.
28.	郑博, 杨卫华, 吴茂念, 等. 基于眼底照相的糖尿病视网膜病变智能辅助诊断技术评价体系的建立及应用[J]. 中华实验眼科杂志, 2019, 37(8): 674-679. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.017.Zheng B, Yang WH, Wu MN, et al. Establishment and application of diabetic retinopathy intelligent assisted diagnostic technology evaluation system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 674-679. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.017.
29.	He J, Baxter SL, Xu J, et al. The practical implementation of artificial intelligence technologies in medicine[J]. Nat Med, 2019, 25(1): 30-36. DOI: 10.1038/s41591-018-0307-0.
30.	Zheng B, Jiang Q, Lu B, et al. Five-category intelligent auxiliary diagnosis model of common fundus diseases based on fundus images[J]. Transl Vis Sci Technol, 2021, 10(7): 20. DOI: 10.1167/tvst.10.7.20.

1. Walter T, Massin P, Erginay A, et al. Automatic detection of microaneurysms in color fundus images[J]. Med Image Anal, 2007, 11(6): 555-566. DOI: 10.1016/j.media.2007.05.001.
2. 邹海东, 何明光. 积极开展社区糖尿病视网膜病变筛查和早期干预工作[J]. 中华眼科杂志, 2016, 52(11): 801-804. DOI: 10.3760/cma.j.issn.0412-4081.2016.11.001.Zou HD, He MG. Active screening and early intervention of diabetic retinopathy in community service[J]. Chin J Ophthalmol, 2016, 52(11): 801-804. DOI: 10.3760/cma.j.issn.0412-4081.2016.11.001.
3. Goldbaum MH, Sample PA, White H, et al. Interpretation of automated perimetry for glaucoma by neural network[J]. Invest Ophthalmol Vis Sci, 1994, 35(9): 3362-3373.
4. LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI: 10.1038/nature14539.
5. 肖璐璐, 窦晓燕. 人工智能在眼部疾病中的应用及其挑战[J]. 国际眼科杂志, 2020, 20(7): 1197-1201. DOI: 10.3980/j.issn.1672-5123.2020.7.18.Xiao LL, Dou XY. Application of artificial Intelligence and deep learning in ophthalmology[J]. Int Eye Sci, 2020, 20(7): 1197-1201. DOI: 10.3980/j.issn.1672-5123.2020.7.18.
6. Elswah DK, Elnakib AA, Moustafa HE. Automated diabetic retinopathy grading using resnet[C]. 2020 37th National Radio Science Conference (NRSC). Cairo: IEEE, 2020: 248-254.
7. Lee T, Jammal AA, Mariottoni EB, et al. Predicting glaucoma development with longitudinal deep learning predictions from fundus photographs[J]. Am J Ophthalmol, 2021, 225: 86-94. DOI: 10.1016/j.ajo.2020.12.031.
8. Nagasato D, Tabuchi H, Ohsugi H, et al. Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion[J]. Int J Ophthalmol, 2019, 12(1): 94-99. DOI: 10.18240/ijo.2019.01.15.
9. Tang Z, Zhang X, Yang G, et al. Automated segmentation of retinal nonperfusion area in fluorescein angiography in retinal vein occlusion using convolutional neural networks[J]. Medical Physics, 2021, 48(2): 648-658. DOI: 10.1002/mp.14640.
10. Li Y, Feng W, Zhao X, et al. Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images[J/OL]. Br J Ophthalmol, 2020, bjophthalmol-2020-317825(2021-06-18)[2021-06-18]. https://bjo.bmj.com/content/bjophthalmol/early/2020/12/20/bjophthalmol-2020-317825.full.pdf. DOI: 10.1136/bjophthalmol-2020-317825. [published online ahead of print].
11. Yim J, Chopra R, Spitz T, et al. Predicting conversion to wet age-related macular degeneration using deep learning[J]. Nat Med, 2020, 26(6): 892-899. DOI: 10.1038/s41591-020-0867-7.
12. Li Z, He Y, Keel S, et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs[J]. Ophthalmology, 2018, 125(8): 1199-1206. DOI: 10.1016/j.ophtha.2018.01.023.
13. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs[J]. JAMA, 2016, 316(22): 2402-2410. DOI: 10.1001/jama.2016.17216.
14. Iandola FN, Han S, Moskewicz MW, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5 MB model size[C]. International Conference on Learning Representations. Toulon: ICLR, 2017: 1-13.
15. Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 2818-2826.
16. Pan SJ, Yang Q. A survey on transfer learning[J]. IEEE T Knowl Data En, 2009, 22(10): 1345-1359. DOI: 10.1109/TKDE.2009.191.
17. Wilkinson CP, Ferris FL 3rd, Klein RE, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales[J]. Ophthalmology, 2003, 110(9): 1677-1682. DOI: 10.1016/S0161-6420(03)00475-5.
18. Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul: ICCV, 2019: 1314-1324.
19. Ma N, Zhang X, Zheng HT, et al. Shufflenet v2: practical guidelines for efficient cnn architecture design[C]. Proceedings of the European Conference on Computer Vision (ECCV). Munich: ECCV, 2018: 116-131.
20. Han K, Wang Y, Tian Q, et al. Ghostnet: more features from cheap operations[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: CVPR, 2020: 1580-1589.
21. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems. Nevada: NIPS, 2012, 25: 1097-1105.
22. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C/OL]. International Conference on Learning Representations, San Diego, 2015[2015-05-07]. https://iclr.cc/archive/www/2015.html.
23. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: CVPR, 2016: 770-778.
24. Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: CVPR, 2017: 4700-4708.
25. 丁喜艳, 杨卫华, 曹国凡, 等. 人工智能在青光眼诊断中的应用[J]. 中国数字医学, 2021, 16(2): 49-53. DOI: 10.3969/j.issn.1673-7571.2021.02.011.Ding XY, Yang WH, Cao GF, et al. Application of artificial intelligence in the diagnosis of glaucoma[J]. Application of New Technology, 2021, 16(2): 49-53. DOI: 10.3969/j.issn.1673-7571.2021.02.011.
26. Cao K, Xu J, Zhao WQ. Artificial intelligence on diabetic retinopathy diagnosis: an automatic classification method based on grey level co-occurrence matrix and naive Bayesian model[J]. Int J Ophthalmol, 2019, 12(7): 1158. DOI: 10.18240/ijo.2019.07.17.
27. Yang WH, Zheng B, Wu MN, et al. An evaluation system of fundus photograph-based intelligent diagnostic technology for diabetic retinopathy and applicability for research[J]. Diabetes Ther, 2019, 10(5): 1811-1822. DOI: 10.1007/s13300-019-0652-0.
28. 郑博, 杨卫华, 吴茂念, 等. 基于眼底照相的糖尿病视网膜病变智能辅助诊断技术评价体系的建立及应用[J]. 中华实验眼科杂志, 2019, 37(8): 674-679. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.017.Zheng B, Yang WH, Wu MN, et al. Establishment and application of diabetic retinopathy intelligent assisted diagnostic technology evaluation system based on fundus photography[J]. Chin J Exp Ophthalmol, 2019, 37(8): 674-679. DOI: 10.3760/cma.j.issn.2095-0160.2019.08.017.
29. He J, Baxter SL, Xu J, et al. The practical implementation of artificial intelligence technologies in medicine[J]. Nat Med, 2019, 25(1): 30-36. DOI: 10.1038/s41591-018-0307-0.
30. Zheng B, Jiang Q, Lu B, et al. Five-category intelligent auxiliary diagnosis model of common fundus diseases based on fundus images[J]. Transl Vis Sci Technol, 2021, 10(7): 20. DOI: 10.1167/tvst.10.7.20.

Chinese Journal of Ocular Fundus Diseases

Research on lightweight model of intelligent-assisted diagnosis of common fundus diseases based on fundus color photography

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content