1. Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs
- Author
-
Valérie Biousse, Nancy J. Newman, Nicolae Sanda, Clare L. Fraser, Chiara La Morgia, John J. Chen, Catherine Clermont-Vignal, Caroline Vasseneix, Pedro Fonseca, Steffen Hamann, Kavin Vanikieti, Raymond P. Najjar, Daniel S W Ting, Dan Milea, Shweta Singhal, Selvakumar Ambika, Masoud Aghsaei Fard, Xinxing Xu, Tien Yin Wong, Carol Y. Cheung, Jiang Zhubo, Philippe Gohier, Marie Bénédicte Rougier, Yong Liu, Ching-Yu Cheng, Wolf A. Lagrèze, Patrick Yu-Wai-Man, Richard Kho, Neil R. Miller, Jost B. Jonas, Hui Yang, Tran Thi Ha Chau, Christophe Chiquet, Luis J. Mejico, Milea, Dan, Najjar, Raymond P, Zhubo, Jiang, Ting, Daniel, Vasseneix, Caroline, Xu, Xinxing, Aghsaei Fard, Masoud, Fonseca, Pedro, Vanikieti, Kavin, Lagrèze, Wolf A, La Morgia, Chiara, Cheung, Carol Y, Hamann, Steffen, Chiquet, Christophe, Sanda, Nicolae, Yang, Hui, Mejico, Luis J, Rougier, Marie-Bénédicte, Kho, Richard, Thi Ha Chau, Tran, Singhal, Shweta, Gohier, Philippe, Clermont-Vignal, Catherine, Cheng, Ching-Yu, Jonas, Jost B, Yu-Wai-Man, Patrick, Fraser, Clare L, Chen, John J, Ambika, Selvakumar, Miller, Neil R, Liu, Yong, Newman, Nancy J, Wong, Tien Y, Biousse, Valérie, BONSAI Group, Amore, Giulia, Carelli, Valerio, Yu Wai Man, Patrick [0000-0001-7847-9320], Apollo - University of Cambridge Repository, and Thumann, Gabriele
- Subjects
Validation study ,FEASIBILITY ,genetic structures ,Fundus Oculi ,Datasets as Topic ,CAMERA ,030204 cardiovascular system & hematology ,Sensitivity and Specificity ,VALIDATION ,LEHA ,Retina ,Direct Ophthalmoscopy ,Diagnosis, Differential ,03 medical and health sciences ,0302 clinical medicine ,Deep Learning ,HEADACHE ,Predictive Value of Tests ,Area under curve ,medicine ,Photography ,Humans ,030212 general & internal medicine ,Papilledema ,papilledema, artificial intelligence, optic disk, optic nerve ,OPHTHALMOSCOPY ,Retrospective Studies ,business.industry ,General Medicine ,EMERGENCY ,eye diseases ,ddc:616.8 ,3. Good health ,Ophthalmoscopy ,Multicenter study ,ROC Curve ,Area Under Curve ,Artificial intelligence ,Neural Networks, Computer ,sense organs ,medicine.symptom ,business ,Algorithms ,DIABETIC-RETINOPATHY - Abstract
BACKGROUND: Nonophthalmologist physicians do not confidently perform direct ophthalmos-copy. The use of artificial intelligence to detect papilledema and other optic-disk abnormalities from fundus photographs has not been well studied METHODS: We trained, validated, and externally tested a deep-learning system to classify optic disks as being normal or having papilledema or other abnormalities from 15,846 retrospectively collected ocular fundus photographs that had been obtained with pharmacologic pupillary dilation and various digital cameras in persons from multiple ethnic populations. Of these photographs, 14,341 from 19 sites in 11 coun-tries were used for training and validation, and 1505 photographs from 5 other sites were used for external testing. Performance at classifying the optic-disk ap-pearance was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity, and specificity, as compared with a reference standard of clinical diagnoses by neuro-ophthalmologists RESULTS: The training and validation data sets from 6779 patients included 14,341 photo-graphs: 9156 of normal disks, 2148 of disks with papilledema, and 3037 of disks with other abnormalities. The percentage classified as being normal ranged across sites from 9.8 to 100%; the percentage classified as having papilledema ranged across sites from zero to 59.5%. In the validation set, the system discriminated disks with papilledema from normal disks and disks with nonpapilledema abnor-malities with an AUC of 0.99 (95% confidence interval [CI], 0.98 to 0.99) and normal from abnormal disks with an AUC of 0.99 (95% CI, 0.99 to 0.99). In the external-testing data set of 1505 photographs, the system had an AUC for the detection of papilledema of 0.96 (95% CI, 0.95 to 0.97), a sensitivity of 96.4% (95% CI, 93.9 to 98.3), and a specificity of 84.7% (95% CI, 82.3 to 87.1).CONCLUSIONSA deep-learning system using fundus photographs with pharmacologically dilated pupils differentiated among optic disks with papilledema, normal disks, and disks with nonpapilledema abnormalities. (Funded by the Singapore National Medical Research Council and the SingHealth Duke–NUS Ophthalmology and Visual Sci-ences Academic Clinical Program.)
- Published
- 2020
- Full Text
- View/download PDF