Automated image curation in diabetic retinopathy screening using deep learning
No Thumbnail Available
Authors
Nderitu, Paul
Nunez do Rio, Joan M.
Webster, Ms Laura
Mann, Samantha S.
Hopkins, David
Cardoso, M. Jorge
Modat, Marc
Bergeles, Christos
Jackson, Timothy L.
Check for full-text access
Issue Date
2022
Type
Article
Language
Keywords
Alternative Title
Abstract
Diabetic retinopathy (DR) screening images are heterogeneous and contain undesirable non-retinal, incorrect field and ungradable samples which require curation, a laborious task to perform manually. We developed and validated single and multi-output laterality, retinal presence, retinal field and gradability classification deep learning (DL) models for automated curation. The internal dataset comprised of 7743 images from DR screening (UK) with 1479 external test images (Portugal and Paraguay). Internal vs external multi-output laterality AUROC were right (0.994 vs 0.905), left (0.994 vs 0.911) and unidentifiable (0.996 vs 0.680). Retinal presence AUROC were (1.000 vs 1.000). Retinal field AUROC were macula (0.994 vs 0.955), nasal (0.995 vs 0.962) and other retinal field (0.997 vs 0.944). Gradability AUROC were (0.985 vs 0.918). DL effectively detects laterality, retinal presence, retinal field and gradability of DR screening images with generalisation between centres and populations. DL models could be used for automated image curation within DR screening.
Description
Citation
Publisher
License
Journal
Scientific Reports
Volume
12
Issue
1