Bayes DeepRetinaNet : A Breakthrough in Bayesian Analysis for Eye Health
International Journal of Imaging Systems and Technology · 2026-11 · 36 (6)
DOI: 10.1002/ima.70456 ↗At a glance
Journal article in International Journal of Imaging Systems and Technology, published online on 2026-11-17. Written by Mariem Qaddour and 3 co-authors. 20 references.
Abstract (original language)
Deep learning has significantly advanced automated retinal disease detection, yet standard convolutional neural networks (CNNs) often lack reliable uncertainty estimation, an essential property in high‐stakes clinical decision‐making. In this paper, we introduce Bayesian DeepRetinaNet, a probabilistic extension of DeepRetinaNet, incorporating Monte Carlo Dropout and Variational Inference for uncertainty‐aware prediction. We evaluate our models on two retinal fundus datasets: APTOS 2019 and DERBI Hackathon. Bayesian variants outperform the baseline CNN in terms of calibration, generalization, and robustness, particularly under noisy or ambiguous conditions. Moreover, qualitative uncertainty analysis reveals that Bayesian models express epistemic uncertainty more effectively, contributing to safer and more interpretable diagnostic outcomes. Our results highlight the clinical potential of integrating Bayesian learning into retinal image analysis pipelines.
Cite
APA
Qaddour, M., Touimi, Y. B., Belmajdoub, H., & Minaoui, K. (2026). Bayes DeepRetinaNet : A Breakthrough in Bayesian Analysis for Eye Health. International Journal of Imaging Systems and Technology, 36(6). https://doi.org/10.1002/ima.70456
Vancouver
Qaddour M, Touimi YB, Belmajdoub H, Minaoui K. Bayes DeepRetinaNet : A Breakthrough in Bayesian Analysis for Eye Health. International Journal of Imaging Systems and Technology. 2026;36(6). doi:10.1002/ima.70456
BibTeX
@article{Qaddour2026,
author = {Qaddour, Mariem and Touimi, Yassine Benjelloune and Belmajdoub, Hanae and Minaoui, Khalid},
title = {Bayes DeepRetinaNet : A Breakthrough in Bayesian Analysis for Eye Health},
journal = {International Journal of Imaging Systems and Technology},
year = {2026},
volume = {36},
number = {6},
doi = {10.1002/ima.70456}
}
EUVIMED