期刊
OPHTHALMOLOGY
卷 129, 期 2, 页码 139-146出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ophtha.2021.07.033
关键词
Artificial intelligence; Corneal scar; Corneal ulcer; Deep learning; Infectious keratitis
资金
- National Eye Institute, National Institutes of Health, Bethesda, Maryland [P30-026877]
- Research to Prevent Blindness, Inc., New York, New York
- National Institutes of Health [K12EY027720, U10EY015114, U10EY018573]
- Knight-Hennessy Scholars at Stanford University, Stanford, California
- JPMorgan Chase Co
This study developed and evaluated an automated, portable algorithm that can differentiate active corneal ulcers from healed scars using only external photographs. The algorithm utilized a convolutional neural network trained on a large dataset of corneal ulcer and scar photographs. The results showed that the algorithm achieved high accuracy in classifying corneal ulcers and scars in diverse patient populations. It demonstrated potential as a cost-effective diagnostic approach that can aid triage in communities with limited access to eye care.
Purpose: To develop and evaluate an automated, portable algorithm to differentiate active corneal ulcers from healed scars using only external photographs. Design: A convolutional neural network was trained and tested using photographs of corneal ulcers and scars. Participants: De-identified photographs of corneal ulcers were obtained from the Steroids for Corneal Ulcers Trial (SCUT), Mycotic Ulcer Treatment Trial (MUTT), and Byers Eye Institute at Stanford University. Methods: Photographs of corneal ulcers (n = 1313) and scars (n = 1132) from the SCUT and MUTT were used to train a convolutional neural network (CNN). The CNN was tested on 2 different patient populations from eye clinics in India (n = 200) and the Byers Eye Institute at Stanford University (n = 101). Accuracy was evaluated against gold standard clinical classifications. Feature importances for the trained model were visualized using gradient-weighted class activation mapping. Main Outcome Measures: Accuracy of the CNN was assessed via F-1 score. The area under the receiver operating characteristic (ROC) curve (AUC) was used to measure the precision-recall trade-off. Results: The CNN correctly classified 115 of 123 active ulcers and 65 of 77 scars in patients with corneal ulcer from India (F-1 score, 92.0% [95% confidence interval (CI), 88.2%-95.8%]; sensitivity, 93.5% [95% CI, 89.1 %-97.9%]; specificity, 84.42% [95% CI, 79.42%-89.42%]; ROC: AUC, 0.9731). The CNN correctly classified 43 of 55 active ulcers and 42 of 46 scars in patients with corneal ulcers from Northern California (F-1 score, 84.3% [95% CI, 77.2%-91.4%]; sensitivity, 78.2% [95% CI, 67.3%-89.1%]; specificity, 91.3% [95% CI, 85.8%-96.8%]; ROC: AUC, 0.9474). The CNN visualizations correlated with clinically relevant features such as corneal infiltrate, hypopyon, and conjunctival injection. Conclusions: The CNN classified corneal ulcers and scars with high accuracy and generalized to patient populations outside of its training data. The CNN focused on clinically relevant features when it made a diagnosis. The CNN demonstrated potential as an inexpensive diagnostic approach that may aid triage in communities with limited access to eye care. (C) 2021 by the American Academy of Ophthalmology
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据