Eye Disease Detection and Classification Optimization Using EfficientNet-B5 with Emphasis on Data Augmentation and Fine-Tuning

Eye Disease Detection and Classification Optimization Using EfficientNet-B5 with Emphasis on Data Augmentation and Fine-Tuning

Automated Diagnosis; Data Augmentation; EfficientNet-B5; Eye Disease Detection; Fine-tuning

ye diseases significant global health challenges, underscoring the need for efficient and accurate diagnostic. This study employed the EfficientNet-B5 model to enhance the detection and classification of eye diseases by incorporating advanced data augmentation and fine-tuning techniques. The research utilizes the ODIR dataset, consisting of 4,217 fundus images categorized into four classes: normal, glaucoma, cataract, and diabetic retinopathy. The methodology comprises three phases: baseline model training, model training with data augmentation, and fine-tuning. The baseline model achieved an accuracy of 60.43%, which improved to 63.03% with data augmentation an increase of 2.6 percentage points. Fine-tuning further elevated the accuracy to 93.23%, representing a notable improvement of 33.8 percentage points over the baseline. Model performance was evaluated using standard classification metrics. These findings demonstrate the technical efficacy of combining augmentation and fine-tuning to enhance model generalization. This result approach offers a robust framework for developing dependable AI-driven diagnostic tools to support early detection and facilitate informed clinical decision-making.

Anggi Muhammad Rifai1, Muhammad Fatchan2, Ahmad Turmudi Zy3, Donny Maulana4, Sufajar Butsianto5

https://jurnal.iaii.or.id/index.php/RESTI/article/view/6519/1148

Department of informatics engineering, Faculty of engineering, Pelita Bangsa University, Bekasi, Indonesia

October 24, 2025

FAJAR BAGUS W

PDF

ENGLISH

TEXT