Preliminary study on the application of artificial intelligence to identify multiple diseases in ultra-widefield fundus images_Chinese Journal of Ocular Fundus Diseases

Authors：

Sun Gongpeng ¹ , Wang Xiaoling ¹ , Xu Lizhang ² , Li Chang ³ , Wang Wenyu ¹ , Yi Zuohuizi ¹ , Zheng Hongmei ¹ , Li Zhiqing ³ ,  Chen Changzheng ¹

1. Eye Center, Renmin Hospital of Wuhan University, Wuhan 430060, China;
2. Wuhan Aiyanbang Technology Co., Ltd, Wuhan 430073, China;
3. Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin International Joint Research and Development Centre of Ophthalmology and Vision Science, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin 300384, China;
Sun Gongpeng and Wang Xiaoling are contributed equally to the article;

Corresponding author：

Chen Changzheng, Email: whuchenchzh@163.com

Keywords：

Retinal diseases; Artificial intelligence; Deep learning; Ultra-widefield fundus images

DOI：

10.3760/cma.j.cn511434-20211228-00728

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To build a small-sample ultra-widefield fundus images (UWFI) multi-disease classification artificial intelligence model, and initially explore the ability of artificial intelligence to classify UWFI multi-disease tasks. Methods A retrospective study. From 2016 to 2021, 1 608 images from 1 123 patients who attended the Eye Center of the Renmin Hospital of Wuhan University and underwent UWFI examination were used for UWFI multi-disease classification artificial intelligence model construction. Among them, 320, 330, 319, 268, and 371 images were used for diabetic retinopathy (DR), retinal vein occlusion (RVO), pathological myopia (PM), retinal detachment (RD), and normal fundus images, respectively. 135 images from 106 patients at the Tianjin Medical University Eye Hospital were used as the external test set. EfficientNet-B7 was selected as the backbone network for classification analysis of the included UWFI images. The performance of the UWFI multi-task classification model was assessed using the receiver operating characteristic curve, area under the curve (AUC), sensitivity, specificity, and accuracy. All data were expressed using numerical values and 95% confidence intervals (CI). The datasets were trained on the network models ResNet50 and ResNet101 and tested on an external test set to compare and observe the performance of EfficientNet with the 2 models mentioned above. Results The overall classification accuracy of the UWFI multi-disease classification artificial intelligence model on the internal and external test sets was 92.57% (95%CI 91.13%-92.92%) and 88.89% (95%CI 88.11%-90.02%), respectively. These were 96.62% and 92.59% for normal fundus, 95.95% and 95.56% for DR, 96.62% and 98.52% for RVO, 98.65% and 97.04% for PM, and 97.30% and 94.07% for RD, respectively. The mean AUC on the internal and external test sets was 0.993 and 0.983, respectively, with 0.994 and 0.939 for normal fundus, 0.999 and 0.995 for DR, 0.985 and 1.000 for RVO, 0.991 and 0.993 for PM and 0.995 and 0.990 for RD, respectively. EfficientNet performed better than the ResNet50 and ResNet101 models on both the internal and external test sets. Conclusion The preliminary UWFI multi-disease classification artificial intelligence model using small samples constructed in this study is able to achieve a high accuracy rate, and the model may have some value in assisting clinical screening and diagnosis.

Citation： Sun Gongpeng, Wang Xiaoling, Xu Lizhang, Li Chang, Wang Wenyu, Yi Zuohuizi, Zheng Hongmei, Li Zhiqing, Chen Changzheng. Preliminary study on the application of artificial intelligence to identify multiple diseases in ultra-widefield fundus images. Chinese Journal of Ocular Fundus Diseases, 2022, 38(2): 132-138. doi: 10.3760/cma.j.cn511434-20211228-00728 Copy

1.	童妍, 卢苇, 邢怡桥, 等. 人工智能在眼科诊断中的应用研究现状[J]. 中华眼底病杂志, 2019, 35(5): 506-509. DOI: 10.3760/cma.j.issn.1005-1015.2019.05.019.Tong Y, Lu W, Xing YQ, et al. Applications of artificial intelligence in the diagnosis of eye diseases[J]. Chin J Ocul Fundus Dis, 2019, 35(5): 506-509. DOI: 10.3760/cma.j.issn.1005-1015.2019.05.019.
2.	Li B, Chen H, Zhang B, et al. Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography[J/OL]. Br J Ophthalmol, 2021, 30: bjophthalmol-2020-316290[2021-03-30]. https://pubmed.ncbi.nlm.nih.gov/33785508/. DOI: 10.1136/bjophthalmol-2020-316290.
3.	Cen LP, Ji J, Lin JW, et al. Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks[J/OL]. Nat Commun, 2021, 12(1): 4828[2021-08-10]. https://pubmed.ncbi.nlm.nih.gov/34376678/. DOI: 10.1038/s41467-021-25138-w.
4.	Lin D, Xiong J, Liu C, et al. Application of comprehensive artificial intelligence retinal expert (CARE) system: a national real-world evidence study[J/OL]. Lancet Digit Health, 2021, 3(8): e486-e495[2021-07-26]. https://pubmed.ncbi.nlm.nih.gov/34325853/. DOI: 10.1016/s2589-7500(21)00086-8.
5.	李占峰, 李志清, 刘巨平, 等. 免散瞳超广角成像系统与免散瞳两个视野45°数码成像系统对糖尿病视网膜病变快速筛查结果的评估[J]. 中华眼底病杂志, 2016, 32(3): 243-247. DOI: 10.3760/cma.j.issn.1005-1015.2016.03.004.Li ZF, Li ZQ, Liu JP, et al. Nonmydriatic ultrawide field retinal imaging system and nonmydriatic two-field digital fundus photography system in a large-scale diabetic retinopathy screening[J]. Chin J Ocul Fundus Dis, 2016, 32(3): 243-247. DOI: 10.3760/cma.j.issn.1005-1015.2016.03.004.
6.	陈珊, 周跃华, 郑燕, 等. 超广角激光扫描检眼镜与间接检眼镜对近视患者眼底病变筛查的比较[J]. 中华实验眼科杂志, 2020, 38(6): 504-509. DOI: 10.3760/cma.j.cn115989-20200512-00333.Chen S, Zhou YH, Zheng Y, et al. Comparison of ultra-wide field laser ophthalmoscopy and indirect ophthalmoscopy for fundus examination of myopia[J]. Chin J Exp Ophthalmol, 2020, 38(6): 504-509. DOI: 10.3760/cma.j.cn115989-20200512-00333.
7.	Li Z, Guo C, Nie D, et al. A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images[J/OL]. Ann Transl Med, 2019, 7(22): 618[2019-11-07]. https://pubmed.ncbi.nlm.nih.gov/31930019/. DOI: 10.21037/atm.2019.11.28.
8.	Li Z, Guo C, Nie D, et al. Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images[J]. Commun Biol, 2020, 3(1): 15. DOI: 10.1038/s42003-019-0730-x.
9.	Li Z, Guo C, Nie D, et al. Development and evaluation of a deep learning system for screening retinal hemorrhage based on ultra-widefield fundus images[J]. Transl Vis Sci Technol, 2020, 9(2): 3. DOI: 10.1167/tvst.9.2.3.
10.	Tang F, Luenam P, Ran AR, et al. Detection of diabetic retinopathy from ultra-widefield scanning laser ophthalmoscope images: a multicenter deep learning analysis[J]. Ophthalmol Retina, 2021, 5(11): 1097-1106. DOI: 10.1016/j.oret.2021.01.013.
11.	Li Z, Guo C, Lin D, et al. Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images[J]. Br J Ophthalmol, 2020, 105(11): 1548-1554. DOI: 10.1136/bjophthalmol-2020-317327.
12.	Ohno-Matsui K, Wu PC, Yamashiro K, et al. IMI pathologic myopia[J]. Invest Ophthalmol Vis Sci, 2021, 62(5): 5. DOI: 10.1167/iovs.62.5.5.
13.	Tan MX, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks[C/OL]//36th International Conference on Machine Learning (ICML), Long Beach, 2019[2019-06-09]. https://arxiv.org/abs/1905.11946.
14.	Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks[J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023. DOI: 10.1109/tpami.2019.2913372.
15.	Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning[J]. Ophthalmology, 2017, 124(7): 962-969. DOI: 10.1016/j.ophtha.2017.02.008.
16.	Nagasawa T, Tabuchi H, Masumoto H, et al. Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naive proliferative diabetic retinopathy[J]. Int Ophthalmol, 2019, 39(10): 2153-2159. DOI: 10.1007/s10792-019-01074-z.
17.	Matsuba S, Tabuchi H, Ohsugi H, et al. Accuracy of ultra-wide-field fundus ophthalmoscopy-assisted deep learning, a machine-learning technology, for detecting age-related macular degeneration[J]. Int Ophthalmol, 2019, 39(6): 1269-1275. DOI: 10.1007/s10792-018-0940-0.
18.	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.
19.	Ohsugi H, Tabuchi H, Enno H, et al. Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment[J/OL]. Sci Rep, 2017, 7(1): 9425[2017-08-25]. https://pubmed.ncbi.nlm.nih.gov/28842613/. DOI: 10.1038/s41598-017-09891-x.
20.	Nagasawa T, Tabuchi H, Masurnoto H, et al. Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes[J/OL]. Peer J, 2018, 6: e5696[2018-10-22]. https://pubmed.ncbi.nlm.nih.gov/30370184/. DOI: 10.7717/peerj.5696.
21.	Nagasato D, Tabuchi H, Ohsugi H, et al. Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy[J/OL]. J Ophthalmol, 2018, 2018: 1875431[2018-11-01]. https://pubmed.ncbi.nlm.nih.gov/30515316/. DOI: 10.1155/2018/1875431.
22.	Zhang W, Zhao X, Chen Y, et al. DeepUWF: an automated ultra-wide-field fundus screening system via deep learning[J]. IEEE J Biomed Health Inform, 2021, 25(8): 2988-2996. DOI: 10.1109/jbhi.2020.3046771.

1. 童妍, 卢苇, 邢怡桥, 等. 人工智能在眼科诊断中的应用研究现状[J]. 中华眼底病杂志, 2019, 35(5): 506-509. DOI: 10.3760/cma.j.issn.1005-1015.2019.05.019.Tong Y, Lu W, Xing YQ, et al. Applications of artificial intelligence in the diagnosis of eye diseases[J]. Chin J Ocul Fundus Dis, 2019, 35(5): 506-509. DOI: 10.3760/cma.j.issn.1005-1015.2019.05.019.
2. Li B, Chen H, Zhang B, et al. Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography[J/OL]. Br J Ophthalmol, 2021, 30: bjophthalmol-2020-316290[2021-03-30]. https://pubmed.ncbi.nlm.nih.gov/33785508/. DOI: 10.1136/bjophthalmol-2020-316290.
3. Cen LP, Ji J, Lin JW, et al. Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks[J/OL]. Nat Commun, 2021, 12(1): 4828[2021-08-10]. https://pubmed.ncbi.nlm.nih.gov/34376678/. DOI: 10.1038/s41467-021-25138-w.
4. Lin D, Xiong J, Liu C, et al. Application of comprehensive artificial intelligence retinal expert (CARE) system: a national real-world evidence study[J/OL]. Lancet Digit Health, 2021, 3(8): e486-e495[2021-07-26]. https://pubmed.ncbi.nlm.nih.gov/34325853/. DOI: 10.1016/s2589-7500(21)00086-8.
5. 李占峰, 李志清, 刘巨平, 等. 免散瞳超广角成像系统与免散瞳两个视野45°数码成像系统对糖尿病视网膜病变快速筛查结果的评估[J]. 中华眼底病杂志, 2016, 32(3): 243-247. DOI: 10.3760/cma.j.issn.1005-1015.2016.03.004.Li ZF, Li ZQ, Liu JP, et al. Nonmydriatic ultrawide field retinal imaging system and nonmydriatic two-field digital fundus photography system in a large-scale diabetic retinopathy screening[J]. Chin J Ocul Fundus Dis, 2016, 32(3): 243-247. DOI: 10.3760/cma.j.issn.1005-1015.2016.03.004.
6. 陈珊, 周跃华, 郑燕, 等. 超广角激光扫描检眼镜与间接检眼镜对近视患者眼底病变筛查的比较[J]. 中华实验眼科杂志, 2020, 38(6): 504-509. DOI: 10.3760/cma.j.cn115989-20200512-00333.Chen S, Zhou YH, Zheng Y, et al. Comparison of ultra-wide field laser ophthalmoscopy and indirect ophthalmoscopy for fundus examination of myopia[J]. Chin J Exp Ophthalmol, 2020, 38(6): 504-509. DOI: 10.3760/cma.j.cn115989-20200512-00333.
7. Li Z, Guo C, Nie D, et al. A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images[J/OL]. Ann Transl Med, 2019, 7(22): 618[2019-11-07]. https://pubmed.ncbi.nlm.nih.gov/31930019/. DOI: 10.21037/atm.2019.11.28.
8. Li Z, Guo C, Nie D, et al. Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images[J]. Commun Biol, 2020, 3(1): 15. DOI: 10.1038/s42003-019-0730-x.
9. Li Z, Guo C, Nie D, et al. Development and evaluation of a deep learning system for screening retinal hemorrhage based on ultra-widefield fundus images[J]. Transl Vis Sci Technol, 2020, 9(2): 3. DOI: 10.1167/tvst.9.2.3.
10. Tang F, Luenam P, Ran AR, et al. Detection of diabetic retinopathy from ultra-widefield scanning laser ophthalmoscope images: a multicenter deep learning analysis[J]. Ophthalmol Retina, 2021, 5(11): 1097-1106. DOI: 10.1016/j.oret.2021.01.013.
11. Li Z, Guo C, Lin D, et al. Deep learning for automated glaucomatous optic neuropathy detection from ultra-widefield fundus images[J]. Br J Ophthalmol, 2020, 105(11): 1548-1554. DOI: 10.1136/bjophthalmol-2020-317327.
12. Ohno-Matsui K, Wu PC, Yamashiro K, et al. IMI pathologic myopia[J]. Invest Ophthalmol Vis Sci, 2021, 62(5): 5. DOI: 10.1167/iovs.62.5.5.
13. Tan MX, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks[C/OL]//36th International Conference on Machine Learning (ICML), Long Beach, 2019[2019-06-09]. https://arxiv.org/abs/1905.11946.
14. Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks[J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023. DOI: 10.1109/tpami.2019.2913372.
15. Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning[J]. Ophthalmology, 2017, 124(7): 962-969. DOI: 10.1016/j.ophtha.2017.02.008.
16. Nagasawa T, Tabuchi H, Masumoto H, et al. Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naive proliferative diabetic retinopathy[J]. Int Ophthalmol, 2019, 39(10): 2153-2159. DOI: 10.1007/s10792-019-01074-z.
17. Matsuba S, Tabuchi H, Ohsugi H, et al. Accuracy of ultra-wide-field fundus ophthalmoscopy-assisted deep learning, a machine-learning technology, for detecting age-related macular degeneration[J]. Int Ophthalmol, 2019, 39(6): 1269-1275. DOI: 10.1007/s10792-018-0940-0.
18. 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.
19. Ohsugi H, Tabuchi H, Enno H, et al. Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment[J/OL]. Sci Rep, 2017, 7(1): 9425[2017-08-25]. https://pubmed.ncbi.nlm.nih.gov/28842613/. DOI: 10.1038/s41598-017-09891-x.
20. Nagasawa T, Tabuchi H, Masurnoto H, et al. Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes[J/OL]. Peer J, 2018, 6: e5696[2018-10-22]. https://pubmed.ncbi.nlm.nih.gov/30370184/. DOI: 10.7717/peerj.5696.
21. Nagasato D, Tabuchi H, Ohsugi H, et al. Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy[J/OL]. J Ophthalmol, 2018, 2018: 1875431[2018-11-01]. https://pubmed.ncbi.nlm.nih.gov/30515316/. DOI: 10.1155/2018/1875431.
22. Zhang W, Zhao X, Chen Y, et al. DeepUWF: an automated ultra-wide-field fundus screening system via deep learning[J]. IEEE J Biomed Health Inform, 2021, 25(8): 2988-2996. DOI: 10.1109/jbhi.2020.3046771.

Chinese Journal of Ocular Fundus Diseases

Preliminary study on the application of artificial intelligence to identify multiple diseases in ultra-widefield fundus images

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content