Screening and diagnostic system construction for optic neuritis and non-arteritic anterior ischemic optic neuropathy based on color fundus images using deep learning_Chinese Journal of Ocular Fundus Diseases

Authors：

Liu Kaiqun ¹ , Liu Shaopeng ² , Tan Xiao ³ , Lin Haotian ¹ ,  Yang Hui ¹

1. State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou 510060, China;
2. School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China;
3. Affiliated Shenzhen Aier Eye Hospital of Jinan University, Shenzhen 51800, China;

Corresponding author：

Yang Hui, Email: yanghui9@hotmail.com

Keywords：

Optic neuritis; Non-arteritic anterior ischemic optic neuropathy; Abnormal optic disc; Artificial intelligence; Deep learning

DOI：

10.3760/cma.j.cn511434-20220505-00265

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To construct and evaluate a screening and diagnostic system based on color fundus images and artificial intelligence (AI)-assisted screening for optic neuritis (ON) and non-arteritic anterior ischemic optic neuropathy (NAION). Methods A diagnostic test study. From 2016 to 2020, 178 cases 267 eyes of NAION patients (NAION group) and 204 cases 346 eyes of ON patients (ON group) were examined and diagnosed in Zhongshan Ophthalmic Center of Sun Yat-sen University; 513 healthy individuals of 1 160 eyes (the normal control group) with normal fundus by visual acuity, intraocular pressure and optical coherence tomography examination were collected from 2018 to 2020. All 2 909 color fundus images were as the data set of the screening and diagnosis system, including 730, 805, and 1 374 images for the NAION group, ON group, and normal control group, respectively. The correctly labeled color fundus images were used as input data, and the EfficientNet-B0 algorithm was selected for model training and validation. Finally, three systems for screening abnormal optic discs, ON, and NAION were constructed. The subject operating characteristic (ROC) curve, area under the ROC (AUC), accuracy, sensitivity, specificity, and heat map were used as indicators of diagnostic efficacy. Results In the test data set, the AUC for diagnosing the presence of an abnormal optic disc, the presence of ON, and the presence of NAION were 0.967 [95% confidence interval (CI) 0.947-0.980], 0.964 (95%CI 0.938-0.979), and 0.979 (95%CI 0.958-0.989), respectively. The activation area of the systems were mainly located in the optic disc area in the decision-making process. Conclusion Abnormal optic disc, ON and NAION, and screening diagnostic systems based on color fundus images have shown accurate and efficient diagnostic performance.

Citation： Liu Kaiqun, Liu Shaopeng, Tan Xiao, Lin Haotian, Yang Hui. Screening and diagnostic system construction for optic neuritis and non-arteritic anterior ischemic optic neuropathy based on color fundus images using deep learning. Chinese Journal of Ocular Fundus Diseases, 2023, 39(1): 51-58. doi: 10.3760/cma.j.cn511434-20220505-00265 Copy

1.	Gordon LK. Optic nerve[J]. Handb Exp Pharmacol, 2017, 242: 369-386. DOI: 10.1007/164_2016_19.
2.	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.
3.	Burlina PM, Joshi N, Pacheco KD, et al. Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration[J]. JAMA Ophthalmol, 2018, 136(12): 1359-1366. DOI: 10.1001/jamaophthalmol.2018.4118.
4.	Brown JM, Campbell JP, Beers A, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks[J]. JAMA Ophthalmol, 2018, 136(7): 803-810. DOI: 10.1001/jamaophthalmol.2018.1934.
5.	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.
6.	Toosy AT, Mason DF, Miller DH. Optic neuritis[J]. Lancet Neurol, 2014, 13(1): 83-99. DOI: 10.1016/S1474-4422(13)70259-X.
7.	Abel A, McClelland C, Lee MS. Critical review: typical and atypical optic neuritis[J]. Surv Ophthalmol, 2019, 64(6): 770-779. DOI: 10.1016/j.survophthal.2019.06.001.
8.	Miller NR, Arnold AC. Current concepts in the diagnosis, pathogenesis and management of nonarteritic anterior ischaemic optic neuropathy[J]. Eye (Lond), 2015, 29(1): 65-79. DOI: 10.1038/eye.2014.144.
9.	Biousse V, Newman NJ. Ischemic optic neuropathies[J]. N Engl J Med, 2015, 372(25): 2428-2436. DOI: 10.1056/NEJMra1413352.
10.	魏世辉, 张晓君, 钟勇, 等. 视神经炎诊断和治疗专家共识(2014年)[J]. 中华眼科杂志, 2014, 50(6): 459-463. DOI: 10.3760/cma.j.issn.0412-4081.2014.06.013.Wei SH, Zhang XJ, Zhong Y, et al. Expert consensus on the diagnosis and treatment of optic neuritis (2014)[J]. Chin J Ophthalmol, 2014, 50(6): 459-463. DOI: 10.3760/cma.j.issn.0412-4081.2014.06.013.
11.	中华医学会眼科学分会神经眼科学组. 我国非动脉炎性前部缺血性视神经病变诊断和治疗专家共识(2015年)[J]. 中华眼科杂志, 2015, 51(5): 323-326. DOI: 10.3760/cma.j.issn.0412-4081.2015.05.002.Neuro-Ophthalmology Group of Chinese Medical Association Ophthalmology Branch. Expert consensus on the diagnosis and treatment of non-arteritic anterior ischemic optic neuropathy in China (2015)[J]. Chin J Ophthalmol, 2015, 51(5): 323-326. DOI: 10.3760/cma.j.issn.0412-4081.2015.05.002.
12.	Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks[EB/OL]. [2020-09-11]. https://arxiv.org/abs/1905.11946.
13.	Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization[EB/OL]. [2016-12-12]. https://ieeexplore.ieee.org/document/7780688.
14.	Milea D, Najjar RP, Zhubo J, et al. Artificial intelligence to detect papilledema from ocular fundus photographs[J]. N Engl J Med, 2020, 382(18): 1687-1695. DOI: 10.1056/NEJMoa1917130.
15.	Akbar S, Akram MU, Sharif M, et al. Decision support system for detection of papilledema through fundus retinal images[J]. J Med Syst, 2017, 41(4): 66. DOI: 10.1007/s10916-017-0712-9.
16.	Fatima KN, Hassan T, Akram MU, et al. Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs[J]. Biomed Opt Express, 2017, 8(2): 1005-1024. DOI: 10.1364/BOE.8.001005.
17.	Ahn JM, Kim S, Ahn KS, et al. Accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema[J/OL]. BMC Ophthalmol, 2019, 19(1): 178[2019-08-09]. https://pubmed.ncbi.nlm.nih.gov/31399077/. DOI: 10.1186/s12886-019-1184-0.
18.	Liu TYA, Wei J, Zhu H, et al. Detection of optic disc abnormalities in color fundus photographs using deep learning[J]. J Neuroophthalmol, 2021, 41(3): 368-374. DOI: 10.1097/WNO.0000000000001358.

1. Gordon LK. Optic nerve[J]. Handb Exp Pharmacol, 2017, 242: 369-386. DOI: 10.1007/164_2016_19.
2. 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.
3. Burlina PM, Joshi N, Pacheco KD, et al. Use of deep learning for detailed severity characterization and estimation of 5-year risk among patients with age-related macular degeneration[J]. JAMA Ophthalmol, 2018, 136(12): 1359-1366. DOI: 10.1001/jamaophthalmol.2018.4118.
4. Brown JM, Campbell JP, Beers A, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks[J]. JAMA Ophthalmol, 2018, 136(7): 803-810. DOI: 10.1001/jamaophthalmol.2018.1934.
5. 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.
6. Toosy AT, Mason DF, Miller DH. Optic neuritis[J]. Lancet Neurol, 2014, 13(1): 83-99. DOI: 10.1016/S1474-4422(13)70259-X.
7. Abel A, McClelland C, Lee MS. Critical review: typical and atypical optic neuritis[J]. Surv Ophthalmol, 2019, 64(6): 770-779. DOI: 10.1016/j.survophthal.2019.06.001.
8. Miller NR, Arnold AC. Current concepts in the diagnosis, pathogenesis and management of nonarteritic anterior ischaemic optic neuropathy[J]. Eye (Lond), 2015, 29(1): 65-79. DOI: 10.1038/eye.2014.144.
9. Biousse V, Newman NJ. Ischemic optic neuropathies[J]. N Engl J Med, 2015, 372(25): 2428-2436. DOI: 10.1056/NEJMra1413352.
10. 魏世辉, 张晓君, 钟勇, 等. 视神经炎诊断和治疗专家共识(2014年)[J]. 中华眼科杂志, 2014, 50(6): 459-463. DOI: 10.3760/cma.j.issn.0412-4081.2014.06.013.Wei SH, Zhang XJ, Zhong Y, et al. Expert consensus on the diagnosis and treatment of optic neuritis (2014)[J]. Chin J Ophthalmol, 2014, 50(6): 459-463. DOI: 10.3760/cma.j.issn.0412-4081.2014.06.013.
11. 中华医学会眼科学分会神经眼科学组. 我国非动脉炎性前部缺血性视神经病变诊断和治疗专家共识(2015年)[J]. 中华眼科杂志, 2015, 51(5): 323-326. DOI: 10.3760/cma.j.issn.0412-4081.2015.05.002.Neuro-Ophthalmology Group of Chinese Medical Association Ophthalmology Branch. Expert consensus on the diagnosis and treatment of non-arteritic anterior ischemic optic neuropathy in China (2015)[J]. Chin J Ophthalmol, 2015, 51(5): 323-326. DOI: 10.3760/cma.j.issn.0412-4081.2015.05.002.
12. Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks[EB/OL]. [2020-09-11]. https://arxiv.org/abs/1905.11946.
13. Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization[EB/OL]. [2016-12-12]. https://ieeexplore.ieee.org/document/7780688.
14. Milea D, Najjar RP, Zhubo J, et al. Artificial intelligence to detect papilledema from ocular fundus photographs[J]. N Engl J Med, 2020, 382(18): 1687-1695. DOI: 10.1056/NEJMoa1917130.
15. Akbar S, Akram MU, Sharif M, et al. Decision support system for detection of papilledema through fundus retinal images[J]. J Med Syst, 2017, 41(4): 66. DOI: 10.1007/s10916-017-0712-9.
16. Fatima KN, Hassan T, Akram MU, et al. Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs[J]. Biomed Opt Express, 2017, 8(2): 1005-1024. DOI: 10.1364/BOE.8.001005.
17. Ahn JM, Kim S, Ahn KS, et al. Accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema[J/OL]. BMC Ophthalmol, 2019, 19(1): 178[2019-08-09]. https://pubmed.ncbi.nlm.nih.gov/31399077/. DOI: 10.1186/s12886-019-1184-0.
18. Liu TYA, Wei J, Zhu H, et al. Detection of optic disc abnormalities in color fundus photographs using deep learning[J]. J Neuroophthalmol, 2021, 41(3): 368-374. DOI: 10.1097/WNO.0000000000001358.

Previous Article
Analysis of the concordance between imaging and histopathologic finds in patients with retinoblastoma optic nerve invasion
Next Article
西藏拉萨早产儿视网膜病变筛查的初步结果

Chinese Journal of Ocular Fundus Diseases

Screening and diagnostic system construction for optic neuritis and non-arteritic anterior ischemic optic neuropathy based on color fundus images using deep learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content