Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

By Zhixi Li, Yifan He, S. Keel, W. Meng, R. Chang, M. He. Ophthalmology (Rochester, Minn.), 2018

728 citations recorded by the source corpus.

PURPOSE To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs. DESIGN A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs. PARTICIPANTS We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm. METHODS This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm. MAIN OUTCOME MEASURES The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON. RESULTS In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%). CONCLUSIONS A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/f550c444c91174592a73df4476f9bc921af3c393

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Chengdi Wang
Kang Zhang
Xiaohong Liu
Lianghong Zheng
Jun Shen
J. He
A. Loewenstein
Y. Zha

Citations in the corpus

Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography (2020, background): “Recent new and exciting advances in the applications of AI in many healthcare areas (Esteva et al., 2019; Gulshan et al., 2016; Li et al., 2018; Norgeot et al., 2019; Poplin et al., 2018; Ravizza et al., 2019; Ting et al., 2017; Topol, 2019) have inspired innovations in the development of novel AI-b”
Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective (2020, background): “…diabetic retinopathy (DR) (Abramoff et al., 2016; Gulshan et al., 2016; Raumviboonsuk et al., 2019; Ting et al., 2017), glaucoma (Liu et al., 2019; Li et al., 2018; Masumoto et al., 2018a; Asaoka et al., 2016), age-related macular degeneration (AMD) (Grassmann et al., 2018; Burlina et al., 2017)…”