An Evaluation System of Fundus Photograph-Based Intelligent Diagnostic Technology for Diabetic Retinopathy and Applicabi
- PDF / 435,984 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 68 Downloads / 188 Views
ORIGINAL RESEARCH
An Evaluation System of Fundus Photograph-Based Intelligent Diagnostic Technology for Diabetic Retinopathy and Applicability for Research Wei-Hua Yang
. Bo Zheng . Mao-Nian Wu . Shao-Jun Zhu .
Fang-Qin Fei . Ming Weng . Xian Zhang . Pei-Rong Lu
Received: April 12, 2019 Ó The Author(s) 2019
ABSTRACT Introduction: In April 2018, the US Food and Drug Administration (FDA) approved the world’s first artificial intelligence (AI) medical device for detecting diabetic retinopathy (DR), the IDx-DR. However, there is a lack of evaluation systems for DR intelligent diagnostic technology. Methods: Five hundred color fundus photographs of diabetic patients were selected. DR Wei-Hua Yang and Bo Zheng contributed equally to this work.
Enhanced Digital Features To view enhanced digital features for this article go to https://doi.org/10.6084/ m9.figshare.8256950. W.-H. Yang P.-R. Lu (&) Department of Ophthalmology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, China e-mail: [email protected] W.-H. Yang Department of Ophthalmology, The First People’s Hospital of Huzhou, Huzhou, Zhejiang, China B. Zheng M.-N. Wu S.-J. Zhu The Information Engineering College of Huzhou University, Huzhou, Zhejiang, China W.-H. Yang B. Zheng M.-N. Wu S.-J. Zhu F.-Q. Fei Key Laboratory of Medical Artificial Intelligence, Huzhou University, Huzhou, Zhejiang, China
severity varied from grade 0 to 4, with 100 photographs for each grade. Following that, these were diagnosed by both ophthalmologists and the intelligent technology, the results of which were compared by applying the evaluation system. The system includes primary, intermediate, and advanced evaluations, of which the intermediate evaluation incorporated two methods. Main evaluation indicators were sensitivity, specificity, and kappa value. Results: The AI technology diagnosed 93 photographs with no DR, 107 with mild non-proliferative DR (NPDR), 107 with moderate NPDR, 108 with severe NPDR, and 85 with proliferative DR (PDR). The sensitivity, specificity, and kappa value of the AI diagnoses in the primary evaluation were 98.8%, 88.0%, and 0.89, respectively. According to method 1 of the M. Weng Department of Ophthalmology, Wuxi Third People’s Hospital, Wuxi, Jiangsu, China X. Zhang Department of Ophthalmology, Ningbo Medical Center Lihuili Eastern Hospital, Ningbo, Zhejiang, China F.-Q. Fei Department of Endocrinology, The First Affiliated Hospital of Huzhou University, Huzhou, Zhejiang, China
Diabetes Ther
intermediate evaluation, the sensitivity of AI diagnosis was 98.0%, specificity 97.0%, and the kappa value 0.95. In method 2 of the intermediate evaluation, the sensitivity of AI diagnosis was 95.5%, the specificity 99.3%, and kappa value 0.95. In the advanced evaluation, the kappa value of the intelligent diagnosis was 0.86. Conclusions: This article proposes an evaluation system for color fundus photograph-based intelligent diagnostic technology of DR and demonstrates an application of this system in a clinical setting. The
Data Loading...
