Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images

Glaucoma is a leading cause of irreversible blindness, making early and accurate detection essential for effective management. This study investigates the use of deep learning for automated glaucoma diagnosis using fundus images from the JustRAIGS challenge dataset, which includes 101442 gradable i...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruxandra-Mădălina FLORESCU, Dragoş-Ovidiu ALEXANDRU, Mircea-Sebastian ŞERBĂNESCU
Format: Article
Language:English
Published: Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca 2025-05-01
Series:Applied Medical Informatics
Subjects:
Online Access:https://ami.info.umfcluj.ro/index.php/AMI/article/view/1185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850102086305316864
author Ruxandra-Mădălina FLORESCU
Dragoş-Ovidiu ALEXANDRU
Mircea-Sebastian ŞERBĂNESCU
author_facet Ruxandra-Mădălina FLORESCU
Dragoş-Ovidiu ALEXANDRU
Mircea-Sebastian ŞERBĂNESCU
author_sort Ruxandra-Mădălina FLORESCU
collection DOAJ
description Glaucoma is a leading cause of irreversible blindness, making early and accurate detection essential for effective management. This study investigates the use of deep learning for automated glaucoma diagnosis using fundus images from the JustRAIGS challenge dataset, which includes 101442 gradable images spanning both referable and non-referable glaucomatous cases. Three convolutional neural networks—ResNet18, GoogLeNet, and AlexNet—were evaluated for their ability to classify glaucomatous and non-glaucomatous eyes. The dataset was divided into 80% for training and validation and 20% for testing, with 10-fold cross-validation used for performance assessment. Among the models, AlexNet achieved the highest accuracy (91.27±3.14%) and AUC (0.95±0.02), outperforming ResNet18 and GoogLeNet. These findings underscore the potential of deep learning in automated glaucoma screening, offering a scalable and efficient diagnostic solution. Future work will integrate clinical input data and explore more advanced classification networks to further enhance diagnostic accuracy and robustness.
format Article
id doaj-art-a85528847a474a44927e3ff0fcbf5b6d
institution DOAJ
issn 2067-7855
language English
publishDate 2025-05-01
publisher Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca
record_format Article
series Applied Medical Informatics
spelling doaj-art-a85528847a474a44927e3ff0fcbf5b6d2025-08-20T02:39:51ZengIuliu Hatieganu University of Medicine and Pharmacy, Cluj-NapocaApplied Medical Informatics2067-78552025-05-0147Suppl. 1Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus ImagesRuxandra-Mădălina FLORESCU0Dragoş-Ovidiu ALEXANDRU1Mircea-Sebastian ŞERBĂNESCU2UMF CraiovaDepartment of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, Petru Rareş Str., no. 2-4, 200349 Craiova, Romania.Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, Petru Rareş Str., no. 2-4, 200349 Craiova, Romania Glaucoma is a leading cause of irreversible blindness, making early and accurate detection essential for effective management. This study investigates the use of deep learning for automated glaucoma diagnosis using fundus images from the JustRAIGS challenge dataset, which includes 101442 gradable images spanning both referable and non-referable glaucomatous cases. Three convolutional neural networks—ResNet18, GoogLeNet, and AlexNet—were evaluated for their ability to classify glaucomatous and non-glaucomatous eyes. The dataset was divided into 80% for training and validation and 20% for testing, with 10-fold cross-validation used for performance assessment. Among the models, AlexNet achieved the highest accuracy (91.27±3.14%) and AUC (0.95±0.02), outperforming ResNet18 and GoogLeNet. These findings underscore the potential of deep learning in automated glaucoma screening, offering a scalable and efficient diagnostic solution. Future work will integrate clinical input data and explore more advanced classification networks to further enhance diagnostic accuracy and robustness. https://ami.info.umfcluj.ro/index.php/AMI/article/view/1185Deep LearningTransfer LearningAutomated DiagnosisFundus Images
spellingShingle Ruxandra-Mădălina FLORESCU
Dragoş-Ovidiu ALEXANDRU
Mircea-Sebastian ŞERBĂNESCU
Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
Applied Medical Informatics
Deep Learning
Transfer Learning
Automated Diagnosis
Fundus Images
title Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
title_full Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
title_fullStr Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
title_full_unstemmed Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
title_short Deep Learning with Transfer Learning for Automated Glaucoma Detection in Fundus Images
title_sort deep learning with transfer learning for automated glaucoma detection in fundus images
topic Deep Learning
Transfer Learning
Automated Diagnosis
Fundus Images
url https://ami.info.umfcluj.ro/index.php/AMI/article/view/1185
work_keys_str_mv AT ruxandramadalinaflorescu deeplearningwithtransferlearningforautomatedglaucomadetectioninfundusimages
AT dragosovidiualexandru deeplearningwithtransferlearningforautomatedglaucomadetectioninfundusimages
AT mirceasebastianserbanescu deeplearningwithtransferlearningforautomatedglaucomadetectioninfundusimages