Evidence Based Prediction and Progression Monitoring on Retinal Images from Three Nations.
AI algorithm
deep learning
diabetes
diabetic retinopathy
lesion detection
Journal
Translational vision science & technology
ISSN: 2164-2591
Titre abrégé: Transl Vis Sci Technol
Pays: United States
ID NLM: 101595919
Informations de publication
Date de publication:
08 2020
08 2020
Historique:
received:
27
01
2020
accepted:
18
06
2020
entrez:
4
9
2020
pubmed:
4
9
2020
medline:
4
9
2020
Statut:
epublish
Résumé
The aim of this work is to demonstrate how a retinal image analysis system, DAPHNE, supports the optimization of diabetic retinopathy (DR) screening programs for grading color fundus photography. Retinal image sets, graded by trained and certified human graders, were acquired from Saudi Arabia, China, and Kenya. Each image was subsequently analyzed by the DAPHNE automated software. The sensitivity, specificity, and positive and negative predictive values for the detection of referable DR or diabetic macular edema were evaluated, taking human grading or clinical assessment outcomes to be the gold standard. The automated software's ability to identify co-pathology and to correctly label DR lesions was also assessed. In all three datasets the agreement between the automated software and human grading was between 0.84 to 0.88. Sensitivity did not vary significantly between populations (94.28%-97.1%) with specificity ranging between 90.33% to 92.12%. There were excellent negative predictive values above 93% in all image sets. The software was able to monitor DR progression between baseline and follow-up images with the changes visualized. No cases of proliferative DR or DME were missed in the referable recommendations. The DAPHNE automated software demonstrated its ability not only to grade images but also to reliably monitor and visualize progression. Therefore it has the potential to assist timely image analysis in patients with diabetes in varied populations and also help to discover subtle signs of sight-threatening disease onset. This article takes research on machine vision and evaluates its readiness for clinical use.
Identifiants
pubmed: 32879754
doi: 10.1167/tvst.9.2.44
pii: TVST-20-2298
pmc: PMC7443119
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Pagination
44Informations de copyright
Copyright 2020 The Authors.
Déclaration de conflit d'intérêts
Disclosure: L. Al Turk, None; S. Wang, None; P. Krause, None; J. Wawrzynski, None; G.M. Saleh, None; H. Alsawadi, None; A.Z. Alshamrani, None; T. Peto, None; A. Bastawrous, None; J. Li, None; H.L. Tang, None
Références
Saudi Med J. 2015 Apr;36(4):449-55
pubmed: 25828282
Br J Ophthalmol. 2020 May 6;:
pubmed: 32376611
NPJ Digit Med. 2018 Aug 28;1:39
pubmed: 31304320
JAMA Ophthalmol. 2013 Mar;131(3):351-7
pubmed: 23494039
Acta Diabetol. 2017 Jun;54(6):515-525
pubmed: 28224275
IEEE Trans Med Imaging. 2008 Sep;27(9):1230-41
pubmed: 18779064
BMC Ophthalmol. 2014 May 01;14:60
pubmed: 24886366
BMJ Open. 2017 Jan 9;7(1):e013199
pubmed: 28069622
Ophthalmology. 1991 May;98(5 Suppl):786-806
pubmed: 2062513
Invest Ophthalmol Vis Sci. 2016 Oct 1;57(13):5200-5206
pubmed: 27701631
JAMA. 2016 Dec 13;316(22):2402-2410
pubmed: 27898976
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
JAMA. 2010 Aug 11;304(6):649-56
pubmed: 20699456
IEEE Trans Biomed Eng. 2017 May;64(5):990-1002
pubmed: 27362756
Curr Diab Rep. 2012 Aug;12(4):338-45
pubmed: 22729994
Diabetes Care. 2015 Mar;38(3):488-94
pubmed: 25524948
Comput Biol Med. 2013 Dec;43(12):2136-55
pubmed: 24290931
PLoS One. 2013 Jul 01;8(7):e66730
pubmed: 23840865