RA-OCTNET: A RELIABILITY-ORIENTED LIGHTWEIGHT ATTENTION NETWORK FOR ROBUST AND EXPLAINABLE RETINAL OCT ANALYSIS
Genetics and Molecular Research · 02.06.2026
DOI: 10.4238/44x8d139 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genetics and Molecular Research, online erschienen am 02.06.2026. Verfasst von Senthilkumar V und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Retinal optical coherence tomography (OCT) is widely used for the diagnosis and monitoring of retinal disease; however, automated OCT classification models require both high discriminative performance and reliability under image-quality variation. This study proposes RA-OCTNet, a robustness-aware attention-enhanced lightweight convolutional neural network for multiclass retinal OCT disease classification. The model incorporates squeeze-and-excitation channel attention, imbalance-sensitive optimisation, corruption-based robustness assessment and Grad-CAM visual explainability. Experiments were conducted on OCTMNIST 64 × 64 images covering choroidal neovascularisation, diabetic macular oedema, drusen and normal retina. RA-OCTNet achieved an accuracy of 0.8500, macro-F1 score of 0.8466 and macro ROC-AUC of 0.9854 using only 1.23 million trainable parameters. Robustness analysis demonstrated comparatively stable performance under contrast variation and occlusion, while Gaussian noise produced the largest degradation. These findings indicate that RA-OCTNet provides a compact, interpretable and reliability-oriented framework for retinal OCT disease classification.
Zitieren
APA
V, S., S, J., Jeeva, A., Manimaran, Sharma, N., A, N., Tripathy, A. K., & Kalra, G. (2026). RA-OCTNET: A RELIABILITY-ORIENTED LIGHTWEIGHT ATTENTION NETWORK FOR ROBUST AND EXPLAINABLE RETINAL OCT ANALYSIS. Genetics and Molecular Research. https://doi.org/10.4238/44x8d139
Vancouver
V S, S J, Jeeva A, Manimaran, Sharma N, A N, et al. RA-OCTNET: A RELIABILITY-ORIENTED LIGHTWEIGHT ATTENTION NETWORK FOR ROBUST AND EXPLAINABLE RETINAL OCT ANALYSIS. Genetics and Molecular Research. 2026. doi:10.4238/44x8d139
BibTeX
@article{V2026,
author = {V, Senthilkumar and S, Jayasundar and Jeeva, A and Manimaran and Sharma, Naresh and A, Nagadeepan and Tripathy, Asesh Kumar and Kalra, Gourav},
title = {RA-OCTNET: A RELIABILITY-ORIENTED LIGHTWEIGHT ATTENTION NETWORK FOR ROBUST AND EXPLAINABLE RETINAL OCT ANALYSIS},
journal = {Genetics and Molecular Research},
year = {2026},
doi = {10.4238/44x8d139}
}
EUVIMED