Publication
Screening for Diabetic Retinopathy Using an Automated Diagnostic System Based on Deep Learning: Diagnostic Accuracy Assessment
| dc.contributor.author | Rêgo, S | |
| dc.contributor.author | Dutra-Medeiros, M | |
| dc.contributor.author | Soares, F | |
| dc.contributor.author | Monteiro-Soares, M | |
| dc.date.accessioned | 2023-04-14T14:38:12Z | |
| dc.date.available | 2023-04-14T14:38:12Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Purpose: To evaluate the diagnostic accuracy of a diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3. Methods: In this cross-sectional study, 295 fundus images were analysed by the CNN model and compared to a panel of ophthalmologists. Images were obtained from a dataset acquired within a screening programme. Diagnostic accuracy measures and respective 95% CI were calculated. Results: The sensitivity and specificity of the CNN model in diagnosing referable DR was 81% (95% CI 66-90%) and 97% (95% CI 95-99%), respectively. Positive predictive value was 86% (95% CI 72-94%) and negative predictive value 96% (95% CI 93-98%). The positive likelihood ratio was 33 (95% CI 15-75) and the negative was 0.20 (95% CI 0.11-0.35). Its clinical impact is demonstrated by the change observed in the pre-test probability of referable DR (assuming a prevalence of 16%) to a post-test probability for a positive test result of 86% and for a negative test result of 4%. Conclusion: A CNN model negative test result safely excludes DR, and its use may significantly reduce the burden of ophthalmologists at reading centres. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.citation | Ophthalmologica . 2021;244(3):250-257. | pt_PT |
| dc.identifier.doi | 10.1159/000512638 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.17/4501 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | Karger | pt_PT |
| dc.subject | HSAC OFT | pt_PT |
| dc.subject | Humans | pt_PT |
| dc.subject | Cross-Sectional Studies | pt_PT |
| dc.subject | Deep Learning* | pt_PT |
| dc.subject | Diabetes Mellitus* | pt_PT |
| dc.subject | Diabetic Retinopathy* / diagnosis | pt_PT |
| dc.subject | Mass Screening | pt_PT |
| dc.subject | Neural Networks, Computer | pt_PT |
| dc.title | Screening for Diabetic Retinopathy Using an Automated Diagnostic System Based on Deep Learning: Diagnostic Accuracy Assessment | pt_PT |
| dc.type | journal article | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 257 | pt_PT |
| oaire.citation.issue | 3 | pt_PT |
| oaire.citation.startPage | 250 | pt_PT |
| oaire.citation.title | Ophthalmologica | pt_PT |
| oaire.citation.volume | 244 | pt_PT |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | article | pt_PT |