RetinalNet-500: A newly developed CNN Model for Eye Disease Detection | IEEE Conference Publication | IEEE Xplore

RetinalNet-500: A newly developed CNN Model for Eye Disease Detection


Abstract:

Fundus images are commonly used by medical experts like ophthalmologists, which are very helpful in detecting various retinal disorders. They used this to diagnose the di...Show More

Abstract:

Fundus images are commonly used by medical experts like ophthalmologists, which are very helpful in detecting various retinal disorders. They used this to diagnose the different types of eye diseases like Cataracts, Diabetic Retinopathy, Glaucoma etc. These fundus images can be also used for the prediction of the severity of the diseases and can provide early signs or warnings. Recently, different machine learning algorithms are playing a vital role in the field of medical science, and it is no different in Ophthalmology either. In this research, we aim to automatically classify healthy and diseased retinal fundus images using deep neural networks. Because deep learning is an excellent machine learning algorithm, which has proven to be very accurate in computer vision problems. In our research, we used convolutional neural networks(CNN) to classify the retinal images whether they are healthy or not.
Date of Conference: 08-09 May 2022
Date Added to IEEE Xplore: 01 June 2022
ISBN Information:
Conference Location: Cairo, Egypt

Contact IEEE to Subscribe

References

References is not available for this document.