From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks
The detection of diabetic retinopathy (DR) is challenging, as the current diagnostic methods rely heavily on the expertise of specialists and require the mass screening of diabetic patients. The prevalence of avoidable vision impairment due to DR necessitates the exploration of alternative diagnosti...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/5/2684 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030913653571584 |
|---|---|
| author | Amira J. Zaylaa Sylva Kourtian |
| author_facet | Amira J. Zaylaa Sylva Kourtian |
| author_sort | Amira J. Zaylaa |
| collection | DOAJ |
| description | The detection of diabetic retinopathy (DR) is challenging, as the current diagnostic methods rely heavily on the expertise of specialists and require the mass screening of diabetic patients. The prevalence of avoidable vision impairment due to DR necessitates the exploration of alternative diagnostic techniques. Specifically, it is necessary to develop reliable automatic methods to enable the early diagnosis and detection of DR from optical images. To address the lack of such methods, this research focused on employing various pre-trained deep neural networks (DNNs) and statistical metrics to provide an automatic framework for detecting DR in optical images. The receiver operating characteristic (ROC) was employed to examine the performance of each network. Ethically obtained real datasets were utilized to validate and enhance the robustness of the proposed detection framework. The experimental results showed that, in terms of the overall performance in DR detection, ResNet-50 was the best, followed by GoogleNet, with 99.44% sensitivity, while they were similar in terms of accuracy (93.56%). ResNet-50 outperformed GoogleNet in terms of the specificity (89.74%) and precision (90.07%) of DR detection. The ROC curves of both ResNet-50 and GoogleNet yielded optimal results, followed by SqueezeNet. MobileNet-v2 showed the weakest performance in terms of the ROC, while all networks showed negligible errors in diagnosis and detection. These results show that the automatic detection and diagnosis framework for DR is a promising tool enabling doctors to diagnose DR early and save time. As future directions, it is necessary to develop a grading algorithm and to explore other strategies to further improve the automatic detection and diagnosis of DR and integrate it into digital slit lamp machines. |
| format | Article |
| id | doaj-art-475a4b64799c4e0da291438f1fc4740c |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-475a4b64799c4e0da291438f1fc4740c2025-08-20T02:59:07ZengMDPI AGApplied Sciences2076-34172025-03-01155268410.3390/app15052684From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural NetworksAmira J. Zaylaa0Sylva Kourtian1Program of Biomedical Engineering, Department of Electrical and Computer Engineering, Faculty of Engineering, Beirut Arab University, Debbieh P.O. Box 11-5020, LebanonCentre de Recherche du Centre Hospitalier, L’Université de Montréal, Montréal, QC H2X 0A9, CanadaThe detection of diabetic retinopathy (DR) is challenging, as the current diagnostic methods rely heavily on the expertise of specialists and require the mass screening of diabetic patients. The prevalence of avoidable vision impairment due to DR necessitates the exploration of alternative diagnostic techniques. Specifically, it is necessary to develop reliable automatic methods to enable the early diagnosis and detection of DR from optical images. To address the lack of such methods, this research focused on employing various pre-trained deep neural networks (DNNs) and statistical metrics to provide an automatic framework for detecting DR in optical images. The receiver operating characteristic (ROC) was employed to examine the performance of each network. Ethically obtained real datasets were utilized to validate and enhance the robustness of the proposed detection framework. The experimental results showed that, in terms of the overall performance in DR detection, ResNet-50 was the best, followed by GoogleNet, with 99.44% sensitivity, while they were similar in terms of accuracy (93.56%). ResNet-50 outperformed GoogleNet in terms of the specificity (89.74%) and precision (90.07%) of DR detection. The ROC curves of both ResNet-50 and GoogleNet yielded optimal results, followed by SqueezeNet. MobileNet-v2 showed the weakest performance in terms of the ROC, while all networks showed negligible errors in diagnosis and detection. These results show that the automatic detection and diagnosis framework for DR is a promising tool enabling doctors to diagnose DR early and save time. As future directions, it is necessary to develop a grading algorithm and to explore other strategies to further improve the automatic detection and diagnosis of DR and integrate it into digital slit lamp machines.https://www.mdpi.com/2076-3417/15/5/2684diabetic retinopathyfundus imagesoptical medical imagingdigital slit lamp machineneural networksdeep learning |
| spellingShingle | Amira J. Zaylaa Sylva Kourtian From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks Applied Sciences diabetic retinopathy fundus images optical medical imaging digital slit lamp machine neural networks deep learning |
| title | From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks |
| title_full | From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks |
| title_fullStr | From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks |
| title_full_unstemmed | From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks |
| title_short | From Pixels to Diagnosis: Early Detection of Diabetic Retinopathy Using Optical Images and Deep Neural Networks |
| title_sort | from pixels to diagnosis early detection of diabetic retinopathy using optical images and deep neural networks |
| topic | diabetic retinopathy fundus images optical medical imaging digital slit lamp machine neural networks deep learning |
| url | https://www.mdpi.com/2076-3417/15/5/2684 |
| work_keys_str_mv | AT amirajzaylaa frompixelstodiagnosisearlydetectionofdiabeticretinopathyusingopticalimagesanddeepneuralnetworks AT sylvakourtian frompixelstodiagnosisearlydetectionofdiabeticretinopathyusingopticalimagesanddeepneuralnetworks |