EUVIMEDEUVIMED entdecken
Crossref

Interpretable Deep Learning for Diabetic Retinopathy Grading using Regression Activation Maps

Muhammad Imran Khalid, Israr Ahmad, Sohaibe Saleem, Altaf Hussain, Syed Akif Hussain, Atif Ali Waghan, Muzamil Khan

ICCK Journal of Image Analysis and Processing · 2025

DOI: 10.62762/jiap.2025.346328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICCK Journal of Image Analysis and Processing, 2025. Verfasst von Muhammad Imran Khalid und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The escalating global prevalence of diabetes renders effective screening for Diabetic Retinopathy (DR) indispensable to prevent irreversible vision loss. Although deep learning models, particularly Convolutional Neural Networks (CNNs), attain diagnostic accuracy comparable to that of human experts, their black-box nature erodes clinical trust. To harmonize accuracy with interpretability, this paper proposes a novel CNN architecture that reformulates DR grading as a regression task. By substituting traditional dense layers with a Global Average Pooling (GAP) layer, our approach substantially reduces model complexity and training time while enabling the generation of Regression Activation Maps (RAMs). These RAMs deliver visual explanations by precisely highlighting the pathological regions that underpin the model's predictions. Evaluated on the Kaggle Diabetic Retinopathy Detection dataset, our model—through the replacement of dense layers with Global Average Pooling—markedly lowers model complexity while delivering diagnostic performance on par with baseline models employing fully-connected layers. The resulting system provides a simpler, more precise, and transparent alternative for automated medical screening, directly associating predictions with clinically relevant features.

Zitieren

APA

Khalid, M. I., Ahmad, I., Saleem, S., Hussain, A., Hussain, S. A., Waghan, A. A., & Khan, M. (2025). Interpretable Deep Learning for Diabetic Retinopathy Grading using Regression Activation Maps. ICCK Journal of Image Analysis and Processing. https://doi.org/10.62762/jiap.2025.346328

Vancouver

Khalid MI, Ahmad I, Saleem S, Hussain A, Hussain SA, Waghan AA, et al. Interpretable Deep Learning for Diabetic Retinopathy Grading using Regression Activation Maps. ICCK Journal of Image Analysis and Processing. 2025. doi:10.62762/jiap.2025.346328

BibTeX
@article{Khalid2025,
  author = {Khalid, Muhammad Imran and Ahmad, Israr and Saleem, Sohaibe and Hussain, Altaf and Hussain, Syed Akif and Waghan, Atif Ali and Khan, Muzamil},
  title = {Interpretable Deep Learning for Diabetic Retinopathy Grading using Regression Activation Maps},
  journal = {ICCK Journal of Image Analysis and Processing},
  year = {2025},
  doi = {10.62762/jiap.2025.346328}
}
Kostenlos starten →