Literature DB >> 33210900

Smartphone-based diabetic macula edema screening with an offline artificial intelligence.

De-Kuang Hwang1,2, Wei-Kuang Yu1,2, Tai-Chi Lin1,2, Shih-Jie Chou2,3, Aliaksandr Yarmishyn3, Zih-Kai Kao2,3, Chung-Lan Kao4,5, Yi-Ping Yang3,6, Shih-Jen Chen1,2, Chih-Chien Hsu1,2, Ying-Chun Jheng3,4,5.   

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.

Entities:  

Year:  2020        PMID: 33210900     DOI: 10.1097/JCMA.0000000000000355

Source DB:  PubMed          Journal:  J Chin Med Assoc        ISSN: 1726-4901            Impact factor:   2.743


  3 in total

1.  [Influence of therapeutic temperature management on the clinical course in patients after in-hospital cardiac arrest : A retrospective analysis].

Authors:  Felix Wanek; Stefanie Meißner; Sebastian Nuding; Sebastian Hoberück; Karl Werdan; Michel Noutsias; Henning Ebelt
Journal:  Med Klin Intensivmed Notfmed       Date:  2021-04-20       Impact factor: 0.840

2.  Commentary: Smartphone imaging integrated with offline artificial intelligence - A boon for the screening of diabetic retinopathy.

Authors:  Kim Ramasamy; Chitaranjan Mishra
Journal:  Indian J Ophthalmol       Date:  2021-11       Impact factor: 1.848

3.  Functional, cognitive, and nutritional decline in 435 elderly nursing home residents after the first wave of the COVID-19 Pandemic.

Authors:  Patricia Pérez-Rodríguez; Macarena Díaz de Bustamante; Salvador Aparicio Mollá; María Caridad Arenas; Susana Jiménez-Armero; Pilar Lacosta Esclapez; Liliana González-Espinoza; Cristina Bermejo Boixareu
Journal:  Eur Geriatr Med       Date:  2021-06-24       Impact factor: 1.710

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.