Development and Validation of a Deep Learning System to Detect Glaucomatous Optic Neuropathy Using Fundus Photographs
Open accessAbstract
Importance: A deep learning system (DLS) that could automatically detect glaucomatous optic neuropathy (GON) with high sensitivity and specificity could expedite screening for GON. Objective: To establish a DLS for detection of GON using retinal fundus images and glaucoma diagnosis with convoluted neural networks (GD-CNN) that has the ability to be generalized across populations. Design, Setting, and Participants: In this cross-sectional study, a DLS for the classification of GON was developed for automated classification of GON using retinal fundus images obtained from the Chinese Glaucoma Study Alliance, the Handan Eye Study, and online databases. The researchers selected 241 032 images were selected as the training data set. The images were entered into the databases on June 9, 2009, obtained on July 11, 2018, and analyses were performed on December 15, 2018. The generalization of the DLS was tested in several validation data sets, which allowed assessment of the DLS in a clinical setting without exclusions, testing against variable image quality based on fundus photographs obtained from websites, evaluation in a population-based study that reflects a natural distribution of patients with glaucoma within the cohort and an additive data set that has a diverse ethnic distribution. An online learning system was established to transfer the trained and validated DLS to generalize the results with fundus images from new sources. To better understand the DLS decision-making process, a prediction visualization test was performed that identified regions of the fundus images utilized by the DLS for diagnosis. Exposures: Use of a deep learning system. Main Outcomes and Measures: Area under the receiver operating characteristics curve (AUC), sensitivity and specificity for DLS with reference to professional graders. Results: From a total of 274 413 fundus images initially obtained from CGSA, 269 601 images passed initial image quality review and were graded for GON. A total of 241 032 images (definite GON 29 865 [12.4%], probable GON 11 046 [4.6%], unlikely GON 200 121 [83%]) from 68 013 patients were selected using random sampling to train the GD-CNN model. Validation and evaluation of the GD-CNN model was assessed using the remaining 28 569 images from CGSA. The AUC of the GD-CNN model in primary local validation data sets was 0.996 (95% CI, 0.995-0.998), with sensitivity of 96.2% and specificity of 97.7%. The most common reason for both false-negative and false-positive grading by GD-CNN (51 of 119 [46.3%] and 191 of 588 [32.3%]) and manual grading (50 of 113 [44.2%] and 183 of 538 [34.0%]) was pathologic or high myopia. Conclusions and Relevance: Application of GD-CNN to fundus images from different settings and varying image quality demonstrated a high sensitivity, specificity, and generalizability for detecting GON. These findings suggest that automated DLS could enhance current screening programs in a cost-effective and time-efficient manner.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
One glaucoma study with six cohorts on retinal fundus photographs provided contingency tables.
“One study34 with six cohorts on RFP provided contingency tables.”
From Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis (2021) · cites this paper as [34]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · see citing works
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · see citing works
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697 · see citing works
The number of people with glaucoma worldwide in 2010 and 2020
Quigley, H. A. (2006) · British Journal of Ophthalmology · doi:10.1136/bjo.2005.081224 · Cited by 7,417 · see citing works
Global Prevalence of Glaucoma and Projections of Glaucoma Burden through 2040
Tham, Y.-C., Li, X., Wong, T. Y., Quigley, H. A., Aung, T., & Cheng, C.-Y. (2014) · Ophthalmology · doi:10.1016/j.ophtha.2014.05.013 · Cited by 7,159 · see citing works
Self-citationThe Pathophysiology and Treatment of Glaucoma: A Review
Weinreb, R. N., Aung, T., & Medeiros, F. A. (2014) · JAMA · doi:10.1001/jama.2014.3192 · Cited by 4,210 · see citing works
Self-citationEhteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293 · see citing works
Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah, H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., et al. (2017) · JAMA · doi:10.1001/jama.2017.18152 · Cited by 2,402 · see citing works
Self-citationImprovements to Platt's SMO Algorithm for SVM Classifier Design
Keerthi, S. S., Shevade, S., Bhattacharyya, C., & Murthy, K. R. K. (2001) · Neural Computation · doi:10.1162/089976601300014493 · Cited by 1,791 · see citing works
Can we open the black box of AI?
Castelvecchi, D. (2016) · Nature · doi:10.1038/538020a · Cited by 1,773 · see citing works
Glaucomatous damage of the macula
Hood, D. C., Raza, A. S., Moraes, C. G. V. D., Liebmann, J. M., & Ritch, R. H. (2012) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2012.08.003 · Cited by 865 · see citing works
Li, Z., He, Y., Keel, S., Meng, W., Chang, R. T., & He, M. (2018) · Ophthalmology · doi:10.1016/j.ophtha.2018.01.023 · Cited by 830 · see citing works
Self-citationWhat This Computer Needs Is a Physician: Humanism and Artificial Intelligence
Verghese, A., Shah, N. H., & Harrington, R. A. (2018) · JAMA · doi:10.1001/jama.2017.19198 · Cited by 468 · see citing works
Glaucoma detection based on deep convolutional neural network
Chen, X., Xu, Y., Wong, D. W. K., Wong, T. Y., & Liu, J. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318462 · Cited by 429 · see citing works
Self-citationGlaucoma risk index:Automated glaucoma detection from color fundus images
Bock, R., Meier, J., Nyúl, L. G., Joachim Hornegger, A., & Michelson, G. (2010) · Medical Image Analysis · doi:10.1016/j.media.2009.12.006 · Cited by 360 · see citing works
Christopher, M., Belghith, A., Bowd, C., Proudfoot, J. A., Goldbaum, M. H., Weinreb, R. N., Girkin, C. A., Liebmann, J. M., & Zangwill, L. M. (2018) · Scientific Reports · doi:10.1038/s41598-018-35044-9 · Cited by 328 · see citing works
Self-citationArtificial Intelligence With Deep Learning Technology Looks Into Diabetic Retinopathy Screening
Wong, T. Y., & Bressler, N. M. (2016) · JAMA · doi:10.1001/jama.2016.17563 · Cited by 271 · see citing works
Self-citationDevelopment of a deep residual learning algorithm to screen for glaucoma from fundus photography
Shibata, N., Tanito, M., Mitsuhashi, K., Fujino, Y., Matsuura, M., Murata, H., & Asaoka, R. (2018) · Scientific Reports · doi:10.1038/s41598-018-33013-w · Cited by 246 · see citing works
Population-based glaucoma prevalence studies in Asians
Cho, H.-K., & Kee, C. (2014) · Survey of Ophthalmology · doi:10.1016/j.survophthal.2013.09.003 · Cited by 239 · see citing works
Singh, A., Dutta, M. K., Mangipudi, P., Uher, V., & Bürget, R. (2015) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2015.10.010 · Cited by 213 · see citing works
Issac, A., Sarathi, M. P., & Dutta, M. K. (2015) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2015.08.002 · Cited by 203 · see citing works
Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review
Haleem, M. S., Han, L., Hemert, J. I. V., & Li, B. (2013) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2013.09.005 · Cited by 186 · see citing works
MRI texture features as biomarkers to predict MGMT methylation status in glioblastomas
Korfiatis, P. D., Kline, T. L., Coufalova, L., Lachance, D. H., Parney, I. F., Carter, R. E., Buckner, J. C., & Erickson, B. J. (2016) · Medical Physics · doi:10.1118/1.4948668 · Cited by 162 · see citing works
Classifying Glaucoma with Image-Based Features from Fundus Photographs
Bock, R., Meier, J., Michelson, G., et al. (2007) · Springer eBooks · doi:10.1007/978-3-540-74936-3_36 · Cited by 104 · see citing works
Strategies for improving early detection of glaucoma: the combined structure–function index
Medeiros, F. A., Tatham, A. J., & Weinreb, R. N. (2014) · Clinical ophthalmology · doi:10.2147/opth.s44586 · Cited by 98 · see citing works
Self-citationIntegrating holistic and local deep features for glaucoma classification
Li, A., Cheng, J. T., Wong, D. W. K., & Liu, J. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7590952 · Cited by 87 · see citing works
Fleming, C. (2005) · The Annals of Family Medicine · doi:10.1370/afm.293 · Cited by 81 · see citing works
Effects of Preprocessing Eye Fundus Images on Appearance Based Glaucoma Classification
Meier, J., Bock, R., Michelson, G., et al. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74272-2_21 · Cited by 55 · see citing works
Zhao, D., Güallar, E., Gajwani, P., et al. (2017) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2017.05.017 · Cited by 45 · see citing works
Chakrabarty, L., Joshi, G. D., Chakravarty, A., Raman, G. V., Krishnadas, S. R., & Sivaswamy, J. (2015) · Journal of Glaucoma · doi:10.1097/ijg.0000000000000354 · Cited by 36 · see citing works
Zhang, Y., Li, S. Z., Li, L., et al. (2014) · Ophthalmic Epidemiology · doi:10.3109/09286586.2014.929707 · Cited by 22 · see citing works
Self-citationWang, N. L., Hao, J., Zhen, Y., et al. (2015) · Journal of Glaucoma · doi:10.1097/ijg.0000000000000351 · Cited by 10 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2022) · Nature Medicine · doi:10.1038/s41591-021-01614-0 · Cited by 3,212 · see citing works
Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis
Aggarwal, R., Sounderajah, V., Martin, G., Ting, D. S. W., Karthikesalingam, A., King, D., Ashrafian, H., & Darzi, A. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00438-z · Cited by 946 · see citing works
Self-citationDigital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective
Li, J.-P. O., Liu, H., Ting, D. S. J., Jeon, S., Chan, R. V. P., Kim, J. E., Sim, D. A., Thomas, P. B. M., Lin, H., Chen, Y., et al. (2021) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2020.100900 · Cited by 626 · see citing works
Self-citationGomez Rossi, J., Rojas-Perilla, N., Krois, J., & Schwendicke, F. (2022) · JAMA Network Open · doi:10.1001/jamanetworkopen.2022.0269 · Cited by 141 · see citing works
González-Gonzalo, C., Thee, E. F., Klaver, C. C. W., Lee, A. Y., Schlingemann, R. O., Tufail, A., Verbraak, F., & Sánchez, C. I. (2022) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2021.101034 · Cited by 103 · see citing works
Protecting Data Privacy in the Age of AI-Enabled Ophthalmology
Tom, E., Keane, P. A., Blazes, M., Pasquale, L. R., Chiang, M. F., Lee, A. Y., Lee, C. S., & and AAO Artificial Intelligence Task Force (2020) · Translational Vision Science & Technology · doi:10.1167/tvst.9.2.36 · Cited by 92 · see citing works
Xiao, X., Xue, L., Ye, L., Li, H., & He, Y. (2021) · BMC Public Health · doi:10.1186/s12889-021-11097-w · Cited by 44 · see citing works
Application of telemedicine in COVID-19: a bibliometric analysis
Lan, X., Yu, H., & Cui, L. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.908756 · Cited by 28 · see citing works
- Authors
- Liu, H., Li, L., Wormstone, I. M., Qiao, C., Zhang, C., Liu, P., Li, S., Wang, H., Mou, D., Pang, R., Yang, D., Zangwill, L. M., Moghimi, S., Hou, H., Bowd, C., Jiang, L., Chen, Y., Hu, M., Xu, Y., Kang, H., Ji, X., Chang, R., Tham, C., Cheung, C., Ting, D. S. W., Wong, T. Y., Wang, Z., Weinreb, R. N., Xu, M., & Wang, N.
- Affiliations
- Beijing Tongren Hospital (CN)
- Beihang University (CN)
- University of East Anglia (GB)
- Peking University Third Hospital (CN)
- Harbin Medical University (CN)
- University of California San Diego (US)
- Capital Medical University (CN)
- Beijing University of Chemical Technology (CN)
- Nankai University (CN)
- Beijing Shanggong Medical Technology Co., Ltd, Beijing, China
- Stanford University (US)
- Chinese University of Hong Kong (HK)
- Singapore National Eye Center (SG)
- Corresponding author
- Xu, Mai
- Wang, Ningli
- ORCID
- Liu, Hanruo
- Li, Liu
- Wormstone, I. Michael
- Zhang, Chun
- Liu, Ping
- Li, Shuning
- Wang, Huaizhou
- Mou, Dapeng
- Pang, Ruiqi
- Zangwill, Linda M.
- Moghimi, Sasan
- Hou, Huiyuan
- Bowd, Christopher
- Jiang, Lai
- Chen, Yihan
- Hu, Man
- Xu, Yongli
- Kang, Hong
- Ji, Xin
- Chang, Robert
- Tham, Clement
- Cheung, Carol
- Ting, Daniel Shu Wei
- Wong, Tien Yin
- Wang, Zulin
- Weinreb, Robert N.
- Xu, Mai
- Wang, Ningli
- Venue
- JAMA Ophthalmology
- Publisher
- American Medical Association (AMA)
- Published
- 2019-12-01
- Volume
- 137
- Issue
- 12
- Pages
- 1353
- ISSN
- 2168-6165 (ISSN-L)
- PMC
- PMC6743057
- OpenAlex
- W2972844301
- Cited by
- 307
- References
- 34
- Citations by year
- 2026: 31 · 2025: 41 · 2024: 55 · 2023: 44 · 2022: 47 · 2021: 46 · 2020: 40 · 2019: 3
- FWCI
- 22.48
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- JAMA Ophthalmology (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- UEA Digital Repository (University of East Anglia) (acceptedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Health Sciences › Medicine › Ophthalmology › Glaucoma and retinal disorders
- Health Sciences › Medicine › Ophthalmology › Ophthalmology and Visual Health Research
- Keywords
- glaucomatous optic neuropathy, glaucoma detection, fundus images, convolutional neural networks, automated diagnosis, model generalization, transfer learning, prediction visualization, image quality, online learning platforms, glaucoma screening, ethnic diversity, model interpretability, sensitivity and specificity
- MeSH terms
- Deep Learning, Cross-Sectional Studies, Diagnostic Techniques, Ophthalmological, False Positive Reactions, Female, Fundus Oculi, Glaucoma, Open-Angle, Humans, Male, Optic Nerve Diseases, Photography, Predictive Value of Tests, ROC Curve, Sensitivity and Specificity, Databases, Factual, Area Under Curve
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
