Clinically applicable artificial intelligence algorithm for the diagnosis, evaluation, and monitoring of acute retinal necrosis

• Published in: Journal of Zhejiang University. B. Science Vol. 22; no. 6; pp. 504 - 511
• Main Authors: Feng, Lei, Zhou, Daizhan, Luo, Chenqi, Shen, Junhui, Wang, Wenzhe, Lu, Yifei, Wu, Jian, Yao, Ke
• Format: Journal Article
• Language: English
• Published: Hangzhou Zhejiang University Press 01.06.2021; Springer Nature B.V; Eye Center,the Second Affiliated Hospital,Zhejiang University School of Medicine,Hangzhou 310009,China%College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China
• Subjects: Algorithms; Aqueous humour; Artificial intelligence; Biomedical and Life Sciences; Biomedicine; Computer applications; Diagnosis; Evaluation; Eye (anatomy); Learning algorithms; Machine learning; Monitoring; Necrosis; Research Article; Retina; Telemedicine; 急性视网膜坏死; 人工智能; 临床应用; Acute retinal necrosis (ARN); Clinical application; Artificial intelligence (AI) algorithm
• ISSN: 1673-1581; 1862-1783; 1862-1783
• DOI: 10.1631/jzus.B2000343

The prompt detection and proper evaluation of necrotic retinal region are especially important for the diagnosis and treatment of acute retinal necrosis (ARN). The potential application of artificial intelligence (AI) algorithms in these areas of clinical research has not been reported previously. The present study aims to create a computational algorithm for the automated detection and evaluation of retinal necrosis from retinal fundus photographs. A total of 149 wide-angle fundus photographs from 40 eyes of 32 ARN patients were collected, and the U-Net method was used to construct the AI algorithm. Thereby, a novel algorithm based on deep machine learning in detection and evaluation of retinal necrosis was constructed for the first time. This algorithm had an area under the receiver operating curve of 0.92, with 86% sensitivity and 88% specificity in the detection of retinal necrosis. For the purpose of retinal necrosis evaluation, necrotic areas calculated by the AI algorithm were significantly positively correlated with viral load in aqueous humor samples ( R 2 =0.7444, P <0.0001) and therapeutic response of ARN ( R 2 = 0.999, P <0.0001). Therefore, our AI algorithm has a potential application in the clinical aided diagnosis of ARN, evaluation of ARN severity, and treatment response monitoring.