Development of a Deep Residual Learning Algorithm to Screen for Glaucoma from Fundus Photography

Overview

Journal Sci Rep

Specialty Science

Date 2018 Oct 4

PMID 30279554

Citations 71

Authors

Naoto Shibata

Masaki Tanito

Keita Mitsuhashi

Yuri Fujino

Masato Matsuura

Hiroshi Murata

Ryo Asaoka

Affiliations

Soon will be listed here.

Abstract

The Purpose of the study was to develop a deep residual learning algorithm to screen for glaucoma from fundus photography and measure its diagnostic performance compared to Residents in Ophthalmology. A training dataset consisted of 1,364 color fundus photographs with glaucomatous indications and 1,768 color fundus photographs without glaucomatous features. A testing dataset consisted of 60 eyes of 60 glaucoma patients and 50 eyes of 50 normal subjects. Using the training dataset, a deep learning algorithm known as Deep Residual Learning for Image Recognition (ResNet) was developed to discriminate glaucoma, and its diagnostic accuracy was validated in the testing dataset, using the area under the receiver operating characteristic curve (AROC). The Deep Residual Learning for Image Recognition was constructed using the training dataset and validated using the testing dataset. The presence of glaucoma in the testing dataset was also confirmed by three Residents in Ophthalmology. The deep learning algorithm achieved significantly higher diagnostic performance compared to Residents in Ophthalmology; with ResNet, the AROC from all testing data was 96.5 (95% confidence interval [CI]: 93.5 to 99.6)% while the AROCs obtained by the three Residents were between 72.6% and 91.2%.

Citing Articles

Deep Learning in Glaucoma Detection and Progression Prediction: A Systematic Review and Meta-Analysis.

Ling X, Chen H, Yeh P, Cheng Y, Huang C, Shen S Biomedicines. 2025; 13(2).

PMID: 40002833 PMC: 11852503. DOI: 10.3390/biomedicines13020420.

Artificial intelligence support improves diagnosis accuracy in anterior segment eye diseases.

Maehara H, Ueno Y, Yamaguchi T, Kitaguchi Y, Miyazaki D, Nejima R Sci Rep. 2025; 15(1):5117.

PMID: 39934383 PMC: 11814138. DOI: 10.1038/s41598-025-89768-6.

The importance of clinical experience in AI-assisted corneal diagnosis: verification using intentional AI misleading.

Maehara H, Ueno Y, Yamaguchi T, Kitaguchi Y, Miyazaki D, Nejima R Sci Rep. 2025; 15(1):1462.

PMID: 39789113 PMC: 11717947. DOI: 10.1038/s41598-025-85827-0.

Artificial Intelligence and Advanced Technology in Glaucoma: A Review.

Tonti E, Tonti S, Mancini F, Bonini C, Spadea L, DEsposito F J Pers Med. 2024; 14(10).

PMID: 39452568 PMC: 11508556. DOI: 10.3390/jpm14101062.

Systematic bibliometric and visualized analysis of research hotspots and trends on the application of artificial intelligence in glaucoma from 2013 to 2022.

Liu C, Wang L, Zhu K, Liu C, Duan J Int J Ophthalmol. 2024; 17(9):1731-1742.

PMID: 39296573 PMC: 11367425. DOI: 10.18240/ijo.2024.09.22.

References

Mitchell P, Hourihan F, Sandbach J, Wang J . The relationship between glaucoma and myopia: the Blue Mountains Eye Study. Ophthalmology. 1999; 106(10):2010-5. DOI: 10.1016/s0161-6420(99)90416-5. View

Xu L, Wang Y, Wang S, Wang Y, Jonas J . High myopia and glaucoma susceptibility the Beijing Eye Study. Ophthalmology. 2006; 114(2):216-20. DOI: 10.1016/j.ophtha.2006.06.050. View

Saito H, Tsutsumi T, Iwase A, Tomidokoro A, Araie M . Correlation of disc morphology quantified on stereophotographs to results by Heidelberg Retina Tomograph II, GDx variable corneal compensation, and visual field tests. Ophthalmology. 2009; 117(2):282-9. DOI: 10.1016/j.ophtha.2009.07.004. View

Takahashi H, Tampo H, Arai Y, Inoue Y, Kawashima H . Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy. PLoS One. 2017; 12(6):e0179790. PMC: 5480986. DOI: 10.1371/journal.pone.0179790. View

Liang Y, Friedman D, Zhou Q, Yang X, Sun L, Guo L . Prevalence of primary open angle glaucoma in a rural adult Chinese population: the Handan eye study. Invest Ophthalmol Vis Sci. 2011; 52(11):8250-7. DOI: 10.1167/iovs.11-7472. View

Gulshan V, Peng L, Coram M, Stumpe M, Wu D, Narayanaswamy A . Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402-2410. DOI: 10.1001/jama.2016.17216. View

Quigley H, Katz J, Derick R, Gilbert D, Sommer A . An evaluation of optic disc and nerve fiber layer examinations in monitoring progression of early glaucoma damage. Ophthalmology. 1992; 99(1):19-28. DOI: 10.1016/s0161-6420(92)32018-4. View

Quigley H, Broman A . The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006; 90(3):262-7. PMC: 1856963. DOI: 10.1136/bjo.2005.081224. View

How A, Tan G, Chan Y, Wong T, Seah S, Foster P . Population prevalence of tilted and torted optic discs among an adult Chinese population in Singapore: the Tanjong Pagar Study. Arch Ophthalmol. 2009; 127(7):894-9. DOI: 10.1001/archophthalmol.2009.134. View

10.

Perera S, Wong T, Tay W, Foster P, Saw S, Aung T . Refractive error, axial dimensions, and primary open-angle glaucoma: the Singapore Malay Eye Study. Arch Ophthalmol. 2010; 128(7):900-5. DOI: 10.1001/archophthalmol.2010.125. View

11.

Huang D, Swanson E, Lin C, Schuman J, Stinson W, Chang W . Optical coherence tomography. Science. 1991; 254(5035):1178-81. PMC: 4638169. DOI: 10.1126/science.1957169. View

12.

Hitchings R, Spaeth G . The optic disc in glaucoma. I: Classification. Br J Ophthalmol. 1976; 60(11):778-85. PMC: 1042838. DOI: 10.1136/bjo.60.11.778. View

13.

Samarawickrama C, Mitchell P, Tong L, Gazzard G, Lim L, Wong T . Myopia-related optic disc and retinal changes in adolescent children from singapore. Ophthalmology. 2011; 118(10):2050-7. DOI: 10.1016/j.ophtha.2011.02.040. View

14.

Rudnicka A, Owen C, Nightingale C, Cook D, Whincup P . Ethnic differences in the prevalence of myopia and ocular biometry in 10- and 11-year-old children: the Child Heart and Health Study in England (CHASE). Invest Ophthalmol Vis Sci. 2010; 51(12):6270-6. PMC: 3055754. DOI: 10.1167/iovs.10-5528. View

15.

Sawada A, Tomidokoro A, Araie M, Iwase A, Yamamoto T . Refractive errors in an elderly Japanese population: the Tajimi study. Ophthalmology. 2008; 115(2):363-370.e3. DOI: 10.1016/j.ophtha.2007.03.075. View

16.

DeLong E, Delong D, Clarke-Pearson D . Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988; 44(3):837-45. View

17.

Hinton G, Osindero S, Teh Y . A fast learning algorithm for deep belief nets. Neural Comput. 2006; 18(7):1527-54. DOI: 10.1162/neco.2006.18.7.1527. View

18.

Ting D, Yim-Lui Cheung C, Lim G, Wei Tan G, Quang N, Gan A . Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA. 2017; 318(22):2211-2223. PMC: 5820739. DOI: 10.1001/jama.2017.18152. View

19.

Asaoka R, Hirasawa K, Iwase A, Fujino Y, Murata H, Shoji N . Validating the Usefulness of the "Random Forests" Classifier to Diagnose Early Glaucoma With Optical Coherence Tomography. Am J Ophthalmol. 2016; 174:95-103. DOI: 10.1016/j.ajo.2016.11.001. View

20.

Asaoka R, Murata H, Iwase A, Araie M . Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier. Ophthalmology. 2016; 123(9):1974-80. DOI: 10.1016/j.ophtha.2016.05.029. View