Detection of Diabetic Retinopathy using Deep ...

Detection of Diabetic Retinopathy using Deep Learning

Author Name : Tushar Rajiv Kumar, Harsh Shekhar Choudhary, Parth Nainesh Shah

DOI: https://doi.org/10.56025/IJARESM.2022.101022981

ABSTRACT

Diabetes mellitus frequently results in diabetic retinopathy (DR), which results in lesions on the retina that impair vision. Blindness may result if it is not caught in time.Unfortunately, there is no cure for DR; treatment merely preserves vision. Early diagnosis and treatment of DR can greatly lower the risk of visual loss. In contrast to computer-aided diagnosis methods, the manual diagnosis of DR retina fundus images by ophthalmologists is time-, effort-, and cost-consuming as well as prone to error.Deep learning has recently risen to prominence as one of the most popular methods for improving performance, particularly in the categorization and interpretation of medical images. Convolutional neural networks are more frequently employed as a deep learning technique in the processing of medical images, and they are quite successful. The most cutting-edge strategies for classifying and detecting DR color fundus images using deep learning techniques have been examined and analyzed for this article. Additionally, the color fundus retina DR datasets have been examined. There are also discussions on several complex subjects that demand further research. From the results of the experiments, the highest accuracy value comes out to be 84%. Our approach produced a precision score of 0.84.

Keywords: Diabetic Retinopathy, Machine Learning, feature extraction, CNN classifier