Convolutional Neural Network for Segmentation and Classification of Glaucoma

Authors

  • Amal Azeroual Department Research Center STIS, M2CS, National Graduate School of Arts and Crafts of Rabat (ENSAM), Biomedical Engineering, Mohammed V University in Rabat, Rabat, Morocco https://orcid.org/0000-0003-2327-0049
  • Younes El Ouahabi Laboratory Health and Biology, Faculty of Sciences, Ibn Tofail University, Kenitra, Morocco
  • Benayad Nsiri Department Research Center STIS, M2CS, National Graduate School of Arts and Crafts of Rabat (ENSAM), Biomedical Engineering, Mohammed V University in Rabat, Rabat, Morocco https://orcid.org/0000-0003-3885-9534
  • Aymane Dakil Department Research Center STIS, M2CS, National Graduate School of Arts and Crafts of Rabat (ENSAM), Biomedical Engineering, Mohammed V University in Rabat, Rabat, Morocco https://orcid.org/0009-0009-2280-1443
  • Moulay Hachem El Yousfi Alaoui Department Research Center STIS, M2CS, National Graduate School of Arts and Crafts of Rabat (ENSAM), Biomedical Engineering, Mohammed V University in Rabat, Rabat, Morocco
  • Abdelmajid Soulaymani Laboratory Health and Biology, Faculty of Sciences, Ibn Tofail University, Kenitra, Morocco https://orcid.org/0000-0002-0964-1029
  • Brahim Benaji Department Research Center STIS, M2CS, National Graduate School of Arts and Crafts of Rabat (ENSAM), Biomedical Engineering, Mohammed V University in Rabat, Rabat, Morocco

DOI:

https://doi.org/10.3991/ijoe.v19i17.43029

Keywords:

glaucoma, U-net model, convolutional neural network, deep learning, image segmentation, image classification

Abstract


Glaucoma is an eye disease that is caused by elevated intraocular pressure and commonly leads to optic nerve damage. Thanks to its vital role in transmitting visual signals from the eye to the brain, the optic nerve is essential for maintaining good and clear vision. Glaucoma is considered one of the leading causes of blindness. Accordingly, the earlier doctors can diagnose and detect the disease, the more feasible its treatment becomes. Aiming to facilitate this task, this study proposes a method for detecting diseases by analyzing images of the interior of the eye using a convolutional neural network. This method consists of segmentation based on a modified U-Net architecture and classification using the DenseNet-201 technique. The proposed model utilized the DRISHTI-GS and RIM-ONE datasets to evaluate glaucoma images. These datasets served as valuable sources of diverse and representative glaucoma-related images, enabling a thorough evaluation of the model’s performance. Finally, the results were highly promising after subjecting the model to a thorough evaluation process. The segmentation accuracy reached 96.65%, while the classification accuracy reached 96.90%. This means that the model excelled in accurately delineating and isolating the relevant regions of interest within the eye images, such as the optical disc and optical cup, which are crucial for diagnosing glaucoma.

Cover iJOE – Vol 19, No 17, 2023

Downloads

Published

2023-12-15

How to Cite

Azeroual, A., El Ouahabi, Y., Nsiri, B., Dakil, A., El Yousfi Alaoui, M. H., Soulaymani, A., & Benaji, B. (2023). Convolutional Neural Network for Segmentation and Classification of Glaucoma. International Journal of Online and Biomedical Engineering (iJOE), 19(17), pp. 19–32. https://doi.org/10.3991/ijoe.v19i17.43029

Issue

Vol. 19 No. 17 (2023)

Section

Papers

License

Copyright (c) 2023 Amal AZEROUAL, Younes El Ouahabi, Benayad Nsiri, Aymane Dakil, Moulay Hachem El Yousfi Alaoui, Abdelmajid Soulaymani, Brahim Benaji

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The submitting author warrants that the submission is original and that she/he is the author of the submission together with the named co-authors; to the extend the submission incorporates text passages, figures, data or other material from the work of others, the submitting author has obtained any necessary permission.
Articles in this journal are published under the Creative Commons Attribution Licence (CC-BY What does this mean?). This is to get more legal certainty about what readers can do with published articles, and thus a wider dissemination and archiving, which in turn makes publishing with this journal more valuable for you, the authors.
By submitting an article the author grants to this journal the non-exclusive right to publish it. The author retains the copyright and the publishing rights for his article without any restrictions.