EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Glaucoma Screening via Optic Disc Localization and Comparative Class Activation Map-Based Analysis

Oscar Ramos-Soto, Ezequiel Perez-Zarate, Jorge Ramos-Frutos, Diego Oliva, Marco Pérez-Cisneros, Guillermo Sosa-Gómez, Sandra E. Balderas-Mata

Machine Learning and Knowledge Extraction · 24.06.2026 · 8 (7) · 173

DOI: 10.3390/make8070173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 24.06.2026. Verfasst von Oscar Ramos-Soto und 6 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Glaucoma, the leading cause of irreversible vision loss, often goes undetected in early stages due to its asymptomatic behaviour. Early diagnosis typically involves visual analysis of the optic disc (OD) in eye fundus images. Machine and deep learning techniques have emerged as valuable tools for automating this process; however, their integration into clinical practice still faces limitations. These challenges include the presence of image regions that are not directly related to glaucoma assessment, such as retinal vasculature, the macula, and background structures, which may introduce irrelevant information and negatively affect classification performance, as well as a general lack of transparency in the decision-making process. This article proposes a methodology that enhances both the accuracy and interpretability of glaucoma detection by focusing solely on the OD region. First, a metaheuristic-based strategy is employed for precise OD detection and cropping, generating an OD-centric dataset with glaucoma-labeled images, which is composed of different public datasets. Four convolutional neural networks (CNNs), namely VGG-19, MobileNet-V2, ResNet-50, and DenseNet-161, are trained on this dataset using transfer learning. To address the need for model explainability, Grad-CAM, Score-CAM, and Eigen-CAM are applied to the trained models to generate post hoc visual explanations of their predictions. The experimental results showed that DenseNet-161 achieved the best overall performance on the assembled public dataset, using an 80%-10%-10% training, validation, and testing split, with a test accuracy of 0.9369 and an AUC of 0.9831. By isolating the OD region and incorporating explainability techniques, the methodology provides a robust and interpretable second opinion, supporting more accurate and efficient glaucoma screening.

Zitieren

APA

Ramos-Soto, O., Perez-Zarate, E., Ramos-Frutos, J., Oliva, D., Pérez-Cisneros, M., Sosa-Gómez, G., & Balderas-Mata, S. E. (2026). Explainable Glaucoma Screening via Optic Disc Localization and Comparative Class Activation Map-Based Analysis. Machine Learning and Knowledge Extraction, 8(7), 173. https://doi.org/10.3390/make8070173

Vancouver

Ramos-Soto O, Perez-Zarate E, Ramos-Frutos J, Oliva D, Pérez-Cisneros M, Sosa-Gómez G, et al. Explainable Glaucoma Screening via Optic Disc Localization and Comparative Class Activation Map-Based Analysis. Machine Learning and Knowledge Extraction. 2026;8(7):173. doi:10.3390/make8070173

BibTeX
@article{RamosSoto2026,
  author = {Ramos-Soto, Oscar and Perez-Zarate, Ezequiel and Ramos-Frutos, Jorge and Oliva, Diego and Pérez-Cisneros, Marco and Sosa-Gómez, Guillermo and Balderas-Mata, Sandra E.},
  title = {Explainable Glaucoma Screening via Optic Disc Localization and Comparative Class Activation Map-Based Analysis},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {7},
  pages = {173},
  doi = {10.3390/make8070173}
}
Kostenlos starten →