Author, as appears in the article.: Baget-Bernaldiz, Marc; Pedro, Romero-Aroca; Santos-Blanco, Esther; Navarro-Gil, Raul; Valls, Aida; Moreno, Antonio; Rashwan, Hatem A.; Puig, Domenec;

Department: Medicina i Cirurgia

URV's Author/s: Moreno Ribas, Antonio / Puig Valls, Domènec Savi / Romero Aroca, Pedro / Valls Mateu, Aïda

Keywords: Validation Sensitivity and specificity Retinography Retina macula lutea Retina image Receiver operating characteristic Prevalence Predictive value Ophthalmologist Non insulin dependent diabetes mellitus Middle aged Male Major clinical study Learning algorithm Image quality Image assessment software Human Guidelines Female False positive result False negative result Eye photography Disease severity Diagnostic test accuracy study Diagnostic accuracy Diabetic retinopathy screening Diabetic retinopathy Diabetic patient Deep learning algorithm Deep learning Data base Convolutional neural networks Convolutional neural network Computer assisted diagnosis Cohort analysis Classifier Classification algorithm Article Aged Adult

Abstract: Background: The aim of the present study was to test our deep learning algorithm (DLA) by reading the retinographies. Methods: We tested our DLA built on convolutional neural networks in 14,186 retinographies from our population and 1200 images extracted from MESSIDOR. The retinal images were graded both by the DLA and independently by four retina specialists. Results of the DLA were compared according to accuracy (ACC), sensitivity (S), specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC), distinguishing between identification of any type of DR (any DR) and referable DR (RDR). Results: The results of testing the DLA for identifying any DR in our population were: ACC = 99.75, S = 97.92, SP = 99.91, PPV = 98.92, NPV = 99.82, and AUC = 0.983. When detecting RDR, the results were: ACC = 99.66, S = 96.7, SP = 99.92, PPV = 99.07, NPV = 99.71, and AUC = 0.988. The results of testing the DLA for identifying any DR with MESSIDOR were: ACC = 94.79, S = 97.32, SP = 94.57, PPV = 60.93, NPV = 99.75, and AUC = 0.959. When detecting RDR, the results were: ACC = 98.78, S = 94.64, SP = 99.14, PPV = 90.54, NPV = 99.53, and AUC = 0.968. Conclusions: Our DLA performed well, both in detecting any DR and in classifying those eyes with RDR in a sample of retinographies of type 2 DM patients in our population and the MESSIDOR database.

Thematic Areas: Medicine, general & internal Clinical biochemistry

licence for use: https://creativecommons.org/licenses/by/3.0/es/

Author's mail: aida.valls@urv.cat pedro.romero@urv.cat domenec.puig@urv.cat antonio.moreno@urv.cat

Author identifier: 0000-0003-3616-7809 0000-0002-7061-8987 0000-0002-0562-4205 0000-0003-3945-2314

Record's date: 2023-03-06

Papper version: info:eu-repo/semantics/publishedVersion

Link to the original source: https://www.mdpi.com/2075-4418/11/8/1385

Licence document URL: http://repositori.urv.cat/ca/proteccio-de-dades/

Papper original source: Diagnostics. 11 (8):

APA: Baget-Bernaldiz, Marc; Pedro, Romero-Aroca; Santos-Blanco, Esther; Navarro-Gil, Raul; Valls, Aida; Moreno, Antonio; Rashwan, Hatem A.; Puig, Domenec; (2021). Testing a Deep Learning Algorithm for Detection of Diabetic Retinopathy in a Spanish Diabetic Population and with MESSIDOR Database. Diagnostics, 11(8), -. DOI: 10.3390/diagnostics11081385

Article's DOI: 10.3390/diagnostics11081385

Entity: Universitat Rovira i Virgili

Journal publication year: 2021

Publication Type: Journal Publications