Sistema de Salut de Catalunya
Institut Català de la Salut
[Font O, Royo D] Optretina Image Reading Team, Barcelona, Spain. [Torrents-Barrena J] BCN MedTech, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain. [Banderas García S] Facultat de Cirurgia i Ciències Morfològiques, Universitat Autònoma de Barcelona, Bellaterra, Spain. Servei d’Oftalmologia, Vall d’Hebron Hospital Universitari, Barcelona, Spain. [Zarranz-Ventura J] Institut Clinic of Ophthalmology (ICOF), Hospital Clinic, Barcelona, Spain. Institut d’Investigacions Biomediques August Pi I Sunyer (IDIBAPS), Barcelona, Spain. [Bures A, Salinas C] Optretina Image Reading Team, Barcelona, Spain. Instituto de Microcirugía Ocular (IMO), Barcelona, Spain. [Zapata MA] Optretina Image Reading Team, Barcelona, Spain. Servei d’Oftalmologia, Vall d’Hebron Hospital Universitari, Barcelona, Spain
Vall d'Hebron Barcelona Hospital Campus
2022-11-07T11:10:11Z
2022-11-07T11:10:11Z
2022-10
Diabetic retinopathy; Retinography; Screening
Retinopatía diabética; Retinografía; Cribado
Retinopatia diabètica; Retinografia; Cribatge
Purpose This study aims to evaluate the ability of an autonomous artificial intelligence (AI) system for detection of the most common central retinal pathologies in fundus photography. Methods Retrospective diagnostic test evaluation on a raw dataset of 5918 images (2839 individuals) evaluated with non-mydriatic cameras during routine occupational health checkups. Three camera models were employed: Optomed Aurora (field of view — FOV 50º, 88% of the dataset), ZEISS VISUSCOUT 100 (FOV 40º, 9%), and Optomed SmartScope M5 (FOV 40º, 3%). Image acquisition took 2 min per patient. Ground truth for each image of the dataset was determined by 2 masked retina specialists, and disagreements were resolved by a 3rd retina specialist. The specific pathologies considered for evaluation were “diabetic retinopathy” (DR), “Age-related macular degeneration” (AMD), “glaucomatous optic neuropathy” (GON), and “Nevus.” Images with maculopathy signs that did not match the described taxonomy were classified as “Other.” Results The combination of algorithms to detect any abnormalities had an area under the curve (AUC) of 0.963 with a sensitivity of 92.9% and a specificity of 86.8%. The algorithms individually obtained are as follows: AMD AUC 0.980 (sensitivity 93.8%; specificity 95.7%), DR AUC 0.950 (sensitivity 81.1%; specificity 94.8%), GON AUC 0.889 (sensitivity 53.6% specificity 95.7%), Nevus AUC 0.931 (sensitivity 86.7%; specificity 90.7%). Conclusion Our holistic AI approach reaches high diagnostic accuracy at simultaneous detection of DR, AMD, and Nevus. The integration of pathology-specific algorithms permits higher sensitivities with minimal impact on its specificity. It also reduces the risk of missing incidental findings. Deep learning may facilitate wider screenings of eye diseases.
Open Access Funding provided by Universitat Autonoma de Barcelona.
Article
Published version
English
Retina - Malalties - Diagnòstic; Intel·ligència artificial; INFORMATION SCIENCE::Information Science::Computing Methodologies::Algorithms::Artificial Intelligence; DISEASES::Eye Diseases::Retinal Diseases; Other subheadings::Other subheadings::/diagnosis; CIENCIA DE LA INFORMACIÓN::Ciencias de la información::metodologías computacionales::algoritmos::inteligencia artificial; ENFERMEDADES::oftalmopatías::enfermedades de la retina; Otros calificadores::Otros calificadores::/diagnóstico
Springer
Graefe's Archive for Clinical and Experimental Ophthalmology;260
https://doi.org/10.1007/s00417-022-05653-2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
Articles científics - HVH [3439]
