A Convolutional Neural Networks (CNNs) approach is proposed to automate the method of Diabetic Retinopathy(DR) screening using color fundus retinal photography as input. Our network uses CNN along with denoising to identify features like micro-aneurysms and haemorrhages on the retina. Our models were developed leveraging Theano, an open source numerical computation library for Python. We trained this network using a high-end GPU on the publicly available Kaggle dataset. On the data set of over 30,000 images our proposed model achieves around 95% accuracy for the two class classification and around 85% accuracy for the five class classification on around 3,000 validation images.
Please cite using following bibtex:
@inproceedings{ghosh2017automatic,
title={Automatic detection and classification of diabetic retinopathy stages using CNN},
author={Ghosh, Ratul and Ghosh, Kuntal and Maitra, Sanjit},
booktitle={2017 4th International Conference on Signal Processing and Integrated Networks (SPIN)},
pages={550--554},
year={2017},
organization={IEEE}
}