JMIR Publications

ABSTRACT

Background:

The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable to screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases.

Objective:

To developed and evaluated an AD model for detecting ocular diseases based on color fundus images.

Methods:

A generative adversarial network (GAN)–based AD method for detecting possible ocular diseases was developed and evaluated using 90499 retinal fundus images derived from four large-scale real-world data sets. Three other independent external test sets were used for external testing and further analysis of the model’s performance in detecting six common ocular diseases (diabetic retinopathy (DR), glaucoma, cataract, age-related macular degeneration (AMD), hypertensive retinopathy (HR), myopia) and DR of different severity levels. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity of the model’s performance were calculated and presented.

Results:

Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in one external proprietary data set. In the detection of six common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR and myopia were 0.891, 0.916, 0.912, 0.867, 0.895 and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR and 0.926 for detecting vision-threatening DR.

Conclusions:

The AD approach achieved high sensitivity and specificity in detecting ocular diseases based on fundus images, meaning that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. In future research, it will be necessary to evaluate the practical applicability of the AD approach in ocular disease screening.