Automated image curation in diabetic retinopathy screening using deep learning

Autor: Paul Nderitu, Joan M. Nunez do Rio, Ms Laura Webster, Samantha S. Mann, David Hopkins, M. Jorge Cardoso, Marc Modat, Christos Bergeles, Timothy L. Jackson
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Scientific Reports, Vol 12, Iss 1, Pp 1-12 (2022)
Druh dokumentu: article
ISSN: 2045-2322
DOI: 10.1038/s41598-022-15491-1
Popis: 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.
Databáze: Directory of Open Access Journals
Nepřihlášeným uživatelům se plný text nezobrazuje