Articles producció científica> Medicina i Cirurgia

Testing a Deep Learning Algorithm for Detection of Diabetic Retinopathy in a Spanish Diabetic Population and with MESSIDOR Database

  • Identification data

    Identifier: imarina:9226625
    Authors:
    Baget-Bernaldiz, MarcPedro, Romero-ArocaSantos-Blanco, EstherNavarro-Gil, RaulValls, AidaMoreno, AntonioRashwan, Hatem APuig, Domenec
    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.
  • Others:

    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: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Baget Bernaldiz, Marc / Moreno Ribas, Antonio / Navarro Gil, Raúl / 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 Internal medicine Clinical biochemistry
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: marc.baget@urv.cat hatem.abdellatif@urv.cat raul.navarrog@estudiants.urv.cat antonio.moreno@urv.cat domenec.puig@urv.cat pedro.romero@urv.cat aida.valls@urv.cat
    Author identifier: 0000-0001-5421-1637 0000-0003-2970-205X 0000-0003-3945-2314 0000-0002-0562-4205 0000-0002-7061-8987 0000-0003-3616-7809
    Record's date: 2024-09-21
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.mdpi.com/2075-4418/11/8/1385
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Diagnostics. 11 (8): 1385-
    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), 1385-. DOI: 10.3390/diagnostics11081385
    Article's DOI: 10.3390/diagnostics11081385
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2021
    Publication Type: Journal Publications
  • Keywords:

    Clinical Biochemistry,Medicine, General & Internal
    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
    Medicine, general & internal
    Internal medicine
    Clinical biochemistry
  • Documents:

  • Cerca a google

    Search to google scholar