Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study

Abstract

Background To verify efficacy of automatic screening and classification of glaucoma with deep learning system. Methods A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicated non-glaucomatous optic neuropathy was excluded. Colour and red-free fundus images were collected for development of DLS and comparison of their efficacy. The convolutional neural network with the pre-trained EfficientNet-b0 model was selected for machine learning. Glaucoma screening (Binary) and ternary classification with or without additional demographics (age, gender, high myopia) were evaluated, followed by creating confusion matrix and heatmaps. Area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score were viewed as main outcome measures. Results Two hundred and twenty-two cases (421 eyes) were enrolled, with 1851 images in total (1207 normal and 644 glaucomatous disc). Train set and test set were comprised of 1539 and 312 images, respectively. If demographics were not provided, AUC, accuracy, precision, sensitivity, F1 score, and specificity of our deep learning system in eye-based glaucoma screening were 0.98, 0.91, 0.86, 0.86, 0.86, and 0.94 in test set. Same outcome measures in eye-based ternary classification without demographic data were 0.94, 0.87, 0.87, 0.87, 0.87, and 0.94 in our test set, respectively. Adding demographics has no significant impact on efficacy, but establishing a linkage between eyes and images is helpful for a better performance. Confusion matrix and heatmaps suggested that retinal lesions and quality of photographs could affect classification. Colour fundus images play a major role in glaucoma classification, compared to red-free fundus images. Conclusions Promising results with high AUC and specificity were shown in distinguishing normal optic nerve from glaucomatous fundus images and doing further classification.

Automated Glaucoma Screening and Diagnosis Based on Retinal Fundus Images Using Deep Learning Approaches: A Comprehensive Review

“…This work also involved the development of a web-based application for locating and diagnosing glaucoma in a limited medical setting. In another work, Hung et al [ 65 ] proposed the use of a pre-trained Efficient-Net-b0 as a base and incorporated additional patient features such as age, gender, and high myopia for binary and ternary classification of glaucoma. The binary classification sub-model task is to distinguish between glaucoma and the non-glaucoma optic disc, whereas the ternary sub-model aims to classify input images into a healthy optic disc, high-tension glaucoma, or normal-tension glaucoma.…”

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

“…To prevent permanent vision loss, early treatment is extremely important. Recently, there have been three common diagnostic techniques for glaucoma including optic nerve head assessment [ 3 ], function-based visual field examination [ 4 , 5 ], and intraocular pressure (IOP) assessment [ 6 , 7 ]. Among these, some manual assessment methods of intraocular pressure measurement have not been widely used due to the differences in the human and equipment resources of each hospital.…”