A deep network DeepOpacityNet for detection of cataracts from color fundus photographs

• Published in: Communications medicine Vol. 3; no. 1; p. 184
• Main Authors: Elsawy, Amr, Keenan, Tiarnan D. L., Chen, Qingyu, Thavikulwat, Alisa T., Bhandari, Sanjeeb, Quek, Ten Cheer, Goh, Jocelyn Hui Lin, Tham, Yih-Chung, Cheng, Ching-Yu, Chew, Emily Y., Lu, Zhiyong
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 16-12-2023; Springer Nature B.V; Nature Portfolio
• Subjects: 692/699/3161/3168; 692/700/139/422; Cataracts; Datasets; Deep learning; Developing countries; LDCs; Medical diagnosis; Medical screening; Medicine; Medicine & Public Health; Ophthalmology; United States > US; Singapore
• ISSN: 2730-664X; 2730-664X
• DOI: 10.1038/s43856-023-00410-w

Background
Cataract diagnosis typically requires in-person evaluation by an ophthalmologist. However, color fundus photography (CFP) is widely performed outside ophthalmology clinics, which could be exploited to increase the accessibility of cataract screening by automated detection.
Methods
DeepOpacityNet was developed to detect cataracts from CFP and highlight the most relevant CFP features associated with cataracts. We used 17,514 CFPs from 2573 AREDS2 participants curated from the Age-Related Eye Diseases Study 2 (AREDS2) dataset, of which 8681 CFPs were labeled with cataracts. The ground truth labels were transferred from slit-lamp examination of nuclear cataracts and reading center grading of anterior segment photographs for cortical and posterior subcapsular cataracts. DeepOpacityNet was internally validated on an independent test set (20%), compared to three ophthalmologists on a subset of the test set (100 CFPs), externally validated on three datasets obtained from the Singapore Epidemiology of Eye Diseases study (SEED), and visualized to highlight important features.
Results
Internally, DeepOpacityNet achieved a superior accuracy of 0.66 (95% confidence interval (CI): 0.64–0.68) and an area under the curve (AUC) of 0.72 (95% CI: 0.70–0.74), compared to that of other state-of-the-art methods. DeepOpacityNet achieved an accuracy of 0.75, compared to an accuracy of 0.67 for the ophthalmologist with the highest performance. Externally, DeepOpacityNet achieved AUC scores of 0.86, 0.88, and 0.89 on SEED datasets, demonstrating the generalizability of our proposed method. Visualizations show that the visibility of blood vessels could be characteristic of cataract absence while blurred regions could be characteristic of cataract presence.
Conclusions
DeepOpacityNet could detect cataracts from CFPs in AREDS2 with performance superior to that of ophthalmologists and generate interpretable results. The code and models are available at
https://github.com/ncbi/DeepOpacityNet
(
https://doi.org/10.5281/zenodo.10127002
).
Plain language summary
Cataracts are cloudy areas in the eye that impact sight. Diagnosis typically requires in-person evaluation by an ophthalmologist. In this study, a computer program was developed that can identify cataracts from specialist photographs of the eye. The computer program successfully identified cataracts and was better able to identify these than ophthalmologists. This computer program could be introduced to improve the diagnosis of cataracts in eye clinics.
Elsawy, Keenan, Chen et al. detect cataracts from color fundus photography using an explainable deep learning network called DeepOpacityNet. DeepOpacityNet detects cataracts more accurately than ophthalmologists and demonstrates that the absence of blood vessels is an indicator that cataracts are present.