Abstract: 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 (R²=0.7444, P<0.0001) and therapeutic response of ARN (R²=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.

人工智能技术在急性视网膜坏死诊治中的应用

[1]AsanoS, YoshikawaT, KimuraH, et al., 2004. Monitoring herpesviruses DNA in three cases of acute retinal necrosis by real-time PCR. J Clin Virol, 29(3):207-210.

[2]BernheimD, GermiR, LabetoulleM, et al., 2013. Time profile of viral DNA in aqueous humor samples of patients treated for varicella-zoster virus acute retinal necrosis by use of quantitative real-time PCR. J Clin Microbiol, 51(7):2160-2166.

[3]BonfioliAA, EllerAW, 2005. Acute retinal necrosis. Semin Ophthalmol, 20(3):155-160.

[4]CalvoCM, KhanMA, MehtaS, et al., 2017. Correlation of clinical outcomes with quantitative polymerase chain reaction DNA copy number in patients with acute retinal necrosis. Ocul Immunol Inflamm, 25(2):246-252.

[5]CulbertsonWW, BlumenkranzMS, HainesH, et al., 1982. The acute retinal necrosis syndrome: Part 2: histopathology and etiology. Ophthalmology, 89(12):1317-1325.

[6]de FauwJ, LedsamJR, Romera-ParedesB, et al., 2018. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med, 24(9):1342-1350.

[7]FalkT, MaiD, BenschR, et al., 2019. U-Net: deep learning for cell counting, detection, and morphometry. Nat Methods, 16(1):67-70.

[8]GulshanV, PengL, CoramM, et al., 2016. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22):2402-2410.

[9]HillenkampJ, NölleB, BrunsC, et al., 2009. Acute retinal necrosis: clinical features, early vitrectomy, and outcomes. Ophthalmology, 116(10):1971-1975.e2.

[10]HollandGN, Executive Committee of the American Uveitis Society, 1994. Standard diagnostic criteria for the acute retinal necrosis syndrome. Am J Ophthalmol, 117(5):663-666.

[11]KanagasingamY, XiaoD, VignarajanJ, et al., 2018. Evaluation of artificial intelligence-based grading of diabetic retinopathy in primary care. JAMA Netw Open, 1(5):e182665.

[12]KermanyDS, GoldbaumM, CaiWJ, et al., 2018. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5):1122-1131.e9.

[13]LeCunY, BengioY, HintonG, 2015. Deep learning. Nature, 521(7553):436-444.

[14]MiserocchiE, IulianoL, FogliatoG, et al., 2019. Bilateral acute retinal necrosis: clinical features and outcomes in a multicenter study. Ocul Immunol Inflamm, 27(7):1090-1098.

[15]PuriI, CoxDD, 2018. A system for accurate tracking and video recordings of rodent eye movements using convolutional neural networks for biomedical image segmentation. Proceedings of 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, p.3590-3593.

[16]RisseeuwS, de BoerJH, ten Dam-van LoonNH, et al., 2019. Risk of rhegmatogenous retinal detachment in acute retinal necrosis with and without prophylactic intervention. Am J Ophthalmol, 206:140-148.

[17]SchaalS, KaganA, WangYJ, et al., 2014. Acute retinal necrosis associated with Epstein-Barr virus: immunohistopathologic confirmation. JAMA Ophthalmol, 132(7):881-882.

[18]SimsJL, YeohJ, StawellRJ, 2009. Acute retinal necrosis: a case series with clinical features and treatment outcomes. Clin Exp Ophthalmol, 37(5):473-477.