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.
Deep Learning; Convolution Neural Networks; Diabetic Retinopathy; Image Classification; Diabetes
U. Satish , SK. Abdul Arafath , 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
U. Satish , SK. Abdul Arafath , V. Rishindra , Y. Mukhesh , V. Sai Harsha "Detection of Diabetic Retinopathy using CNN" Iconic Research And Engineering Journals, 3(11)