Computer Aided Diagnosis System for Diabetic Retinopathy using Deep Learning-based CNN Method

Diabetic Retinopathy (DR) is one of the major causes of blindness in the world. Regular screening of diabetic patients for DR has been shown to be a cost-eô€€€ective and important aspect of their care. The accuracy and timing of this care is of significant importance to both the cost and eô€€€ectiveness of treatment. The diagnosis of diabetic retinopathy through colour 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 diô€€€cult and time-consuming task. The main objective of this paper is deep learning-based CNN method is introduced for the problem of classifying DR in fundus imagery. This is a medical imaging task with increasing diagnostic relevance .With the help of Convolutional Neural Networks (CNN) approach to diagnosing DR from digital fundus images and accurately classifying its severity. A network is developed with CNN architecture which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input. This network is trained on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task.