Smartphone-based diabetic macula edema screening with an offline artificial intelligence. Issue 12 (29th May 2020)

• Record Type: Journal Article
• Authors: Hwang, De-Kuang; Yu, Wei-Kuang; Lin, Tai-Chi; Chou, Shih-Jie; Yarmishyn, Aliaksandr; Kao, Zih-Kai; Kao, Chung-Lan; Yang, Yi-Ping; Chen, Shih-Jen; Hsu, Chih-Chien; Jheng, Ying-Chun
• Is Part Of: Journal of the Chinese Medical Association. Volume 83:Issue 12(2020)
• Page Start: 1102
• Page End: 1106
• Publication Date: 2020-05-29
• Subjects: Artificial intelligence -- Diabetic macular edema -- Optical coherence tomography -- Smartphone; Medicine -- Periodicals; 610.5
• DOI: 10.1097/JCMA.0000000000000355
• Languages: English
• ISSNs: 1726-4901

Abstract

Abstract : Background: Diabetic macular edema (DME) is a sight-threatening condition that needs regular examinations and remedies. Optical coherence tomography (OCT) is the most common used examination to evaluate the structure and thickness of the macula, but the software in the OCT machine does not tell the clinicians whether DME exists directly. Recently, artificial intelligence (AI) is expected to aid in diagnosis generation and therapy selection. We thus develop a smartphone-based offline AI system that provides diagnostic suggestions and medical strategies through analyzing OCT images from diabetic patients at the risk of developing DME. Methods: DME patients receiving treatments in 2017 at Taipei Veterans General Hospital were included in this study. We retrospectively collected the OCT images of these patients from January 2008 to July 2018. We established the AI model based on MobileNet architecture to classify the OCT images conditions. The confusion matrix has been applied to present the performance of the trained AI model. Results: Based on the convolutional neural network with the MobileNet model, our AI system achieved a high DME diagnostic accuracy of 90.02%, which is comparable to other AI systems such as InceptionV3 and VGG16. We further developed a mobile-application based on this AI model available at https://aicl.ddns.net/DME.apk . Conclusion: We successful integrated an AI model into the mobile device to provide an offline method to provide the diagnosis for quickly screening the risk of developing DME. With the offline property, our model could help those nonophthalmological healthcare providers in offshore islands or underdeveloped countries.