Hybrid Machine Learning Model for Retinal Detachment and Diabetic Retinopathy Detection

Radha J., Lathiga L., Madheswaran M., Naveen Kumar S.

2025

Abstract

Retinal Detachment (RD) and Diabetic Retinopathy (DR) are some of the major causes of blindness and thus require early diagnosis in order to avoid serious complications. This paper proposed a hybrid deep learning and machine learning model with better pre-processing techniques for automated detection of DR and RD. This model incorporates circular cropping, Ben’s preprocessing, and data augmentation to boost the model's performance. Using InceptionV3, the Diabetic Retinopathy model achieved 88% accuracy on the APTOS2019 dataset. The Clinically validated datasets of Retinal Detachment models achieved 83% accuracy using MobileNetV2. The two-model architecture enables simultaneous diagnosis and error free retinal image analyses with minimal time. Proposed methods were tested, and the results confirm its effectiveness for real life clinical retinal disease detection and classification.

Paper Citation

in Harvard Style

J. R., L. L., M. M. and S. N. (2025). Hybrid Machine Learning Model for Retinal Detachment and Diabetic Retinopathy Detection. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 232-237. DOI: 10.5220/0013880600004919

in Bibtex Style

@conference{icrdicct`2525,
author={Radha J. and Lathiga L. and Madheswaran M. and Naveen S.},
title={Hybrid Machine Learning Model for Retinal Detachment and Diabetic Retinopathy Detection},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={232-237},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013880600004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Hybrid Machine Learning Model for Retinal Detachment and Diabetic Retinopathy Detection
SN - 978-989-758-777-1
AU - J. R.
AU - L. L.
AU - M. M.
AU - S. N.
PY - 2025
SP - 232
EP - 237
DO - 10.5220/0013880600004919
PB - SciTePress