Detection of Diabetic Retinopathy using CNN

• Author(s): U. Satish; S K. Abbddularafath; V. Rishindra; Y. Mukhesh; V. Sai Harsha
• Paper ID: 1702295
• Page: 86-92
• Published Date: 15-05-2020
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 3 Issue 11 May-2020

Abstract

The diagnosis the diagnosis of diabetic retinopathy (DR) through color fundus images requires experienced clinicians to identify the presence and significance of many small features which, along with a complex grading system, makes this a difficult and time-consuming task. In this paper, we propose a CNN approach to diagnosing DR from digital fundus images and accurately classifying its severity. We develop a network with CNN architecture and data augmentation which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and hemorrhage on the retina and consequently provide a diagnosis automatically and without user input. We train this network using a high-end graphics processor unit (GPU) on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task. On the data set of 80,000 images used our proposed CNN achieves a sensitivity of 95% and an accuracy of 75% on 5,000 validation images.

Keywords

Deep Learning; Convolution Neural Networks; Diabetic Retinopathy; Image Classification; Diabetes

Citations

IRE Journals:
U. Satish, S K. Abbddularafath, V. Rishindra, Y. Mukhesh, V. Sai Harsha "Detection of Diabetic Retinopathy using CNN" Iconic Research And Engineering Journals Volume 3 Issue 11 2020 Page 86-92

IEEE:
U. Satish, S K. Abbddularafath, V. Rishindra, Y. Mukhesh, V. Sai Harsha "Detection of Diabetic Retinopathy using CNN" Iconic Research And Engineering Journals, vol. 3, no. 11, May. 2020

APA:
U. Satish, S K. Abbddularafath, V. Rishindra, Y. Mukhesh, V. Sai Harsha (2020). Detection of Diabetic Retinopathy using CNN. Iconic Research And Engineering Journals, 3(11).

MLA:
U. Satish, S K. Abbddularafath, V. Rishindra, Y. Mukhesh, V. Sai Harsha "Detection of Diabetic Retinopathy using CNN" Iconic Research And Engineering Journals, vol. 3, no. 11, May. 2020.

BibTeX

@article{1702295,
author = {U. Satish, S K. Abbddularafath, V. Rishindra, Y. Mukhesh, V. Sai Harsha},
title = {Detection of Diabetic Retinopathy using CNN},
journal = {Iconic Research And Engineering Journals},
year = {2020},
volume = {3},
number = {11},
pages = {86-92},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/17022951.pdf},
abstract = {The diagnosis the diagnosis of diabetic retinopathy (DR) through color fundus images requires experienced clinicians to identify the presence and significance of many small features which, along with a complex grading system, makes this a difficult and time-consuming task. In this paper, we propose a CNN approach to diagnosing DR from digital fundus images and accurately classifying its severity. We develop a network with CNN architecture and data augmentation which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and hemorrhage on the retina and consequently provide a diagnosis automatically and without user input. We train this network using a high-end graphics processor unit (GPU) on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task. On the data set of 80,000 images used our proposed CNN achieves a sensitivity of 95% and an accuracy of 75% on 5,000 validation images.},
keywords = {Deep Learning; Convolution Neural Networks; Diabetic Retinopathy; Image Classification; Diabetes},
month = {May}
}