On the value of deep learning for diagnosing diabetic retinopathy

TitreOn the value of deep learning for diagnosing diabetic retinopathy
Publication TypeJournal Article
Year of Publication2022
AuthorsLahmar, C, Idri, A
JournalHealth and Technology
Volume12
Pagination89-105
Mots-clésArticle, Binary classification, comparative effectiveness, controlled study, Convolutional neural network, Deep learning, densenet201, Diabetic retinopathy, diagnostic accuracy, diagnostic test accuracy study, diagnostic value, human, inception resnet v2, inception v3, k fold cross validation, mobilenet v2, residual neural network, resnet50, sensitivity and specificity, vgg16, vgg19
Abstract

Diabetic retinopathy (DR) is one of the main causes of vision loss around the world. The early diagnosis of this disease can help in treating it efficiently. Deep learning (DL) is rapidly becoming the state of the art, leading to enhanced performance in various medical applications such as diabetic retinopathy and breast cancer. In this paper, we conduct an empirical evaluation of seven convolutional neural networks (CNN) architectures for an automatic binary classification of the referable diabetic retinopathy; the DL architectures (Inception_ResNet_V2, Inception_V3, ResNet50, VGG16, VGG19, MobileNet_V2 and DenseNet201) were evaluated and compared in terms of accuracy, sensitivity, specificity, precision and F1-score using the Scott Knott test and the Borda count voting method. All the empirical evaluations were over three datasets: APTOS, Kaggle DR and the Messidor-2, using a k-fold cross validation method. Experiments showed the importance of using deep learning in the classification of DR since the seven models gave a high accuracy values. Furthermore, DenseNet201 and mobileNet_V2 were the top two performing techniques respectively. DenseNet201 provided the best performance for the Kaggle and Messidor-2 datasets with an accuracy equal to 84.74% and 85.79% respectively. MobileNet_V2 provided the best performance in the APTOS dataset with an accuracy equal to 93.09%. As for the ResNet50, Inception_V3 and Inception_ResNet_V2, they were the worst performing compared to the other DL techniques. Therefore, we recommend the use of DenseNet201 and MobileNet_V2 for the detection of the referable DR since they provided the best performances on the three datasets. © 2021, IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature.

URLhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85116986540&doi=10.1007%2fs12553-021-00606-x&partnerID=40&md5=0a388e86c6b6b49bc1f026a6defbfa2d
DOI10.1007/s12553-021-00606-x
Revues: 

Partenaires

Localisation

Suivez-nous sur

         

    

Contactez-nous

ENSIAS

Avenue Mohammed Ben Abdallah Regragui, Madinat Al Irfane, BP 713, Agdal Rabat, Maroc

  Télécopie : (+212) 5 37 68 60 78

  Secrétariat de direction : 06 61 48 10 97

        Secrétariat général : 06 61 34 09 27

        Service des affaires financières : 06 61 44 76 79

        Service des affaires estudiantines : 06 62 77 10 17 / n.mhirich@um5s.net.ma

        Résidences : 06 61 82 89 77

Contacts

    

Education - This is a contributing Drupal Theme
Design by WeebPal.