Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study (Preprint)
Preprint
- 8 February 2021
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
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 for 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 This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images. METHODS A generative adversarial network–based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model’s performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. 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 1 external proprietary data set. In the detection of 6 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 on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening.Keywords
All Related Versions
- Published version: Journal of Medical Internet Research, 23 (7), e27822.
This publication has 37 references indexed in Scilit:
- Automated Analysis of Retinal Images for Detection of Referable Diabetic RetinopathyJAMA Ophthalmology, 2013
- Comparison of Supervised and Unsupervised Learning Algorithms for Pattern ClassificationInternational Journal of Advanced Research in Artificial Intelligence, 2013
- Diabetic retinopathy management guidelinesExpert Review of Ophthalmology, 2012
- Detection of Pathological Myopia by PAMELA with Texture‐Based Features through an SVM ApproachJournal of Healthcare Engineering, 2010
- The coming of age of artificial intelligence in medicineArtificial Intelligence in Medicine, 2009
- Evaluation of the Clinical Age-Related Maculopathy Staging SystemOphthalmology, 2006
- Detecting cataract causing visual impairment using a nonmydriatic fundus cameraAmerican Journal of Ophthalmology, 2005
- A Survey of Outlier Detection MethodologiesArtificial Intelligence Review, 2004
- Novelty detection: a review—part 1: statistical approachesSignal Processing, 2003
- Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scalesOphthalmology, 2003