Main Article Content
Diabetic retinopathy is one of the most threatening complications of diabetes that leads to permanent blindness if leftuntreated. One of the essential challenges is early detection, which is very important for treatment success. Unfortunately, the exactidentification of the diabetic retinopathy stage is notoriously tricky and requires expert human interpretation of fundus images. Simplification of the detection step is crucial and can help millions of people. In this project we propose an automatic deep-learning-based method for stage detection of diabetic retinopathy by single photography of the human fundus.Convolutional neural networks (CNN) have been successfully applied in many adjacent subjects, and for diagnosis of diabetic retinopathy itself. However, the high cost of big labeled datasets, as well as inconsistency between different doctors, impede the performanceof thesemethods. Inthis project we propose anautomatic deep-learning-based method for stage detection of diabetic retinopathy by single photography of the human fundus. In this system, we analyzed diabetes detectability from retinal images in the Diabetic Retinopathy Database - Calibration Level Raw pixel intensities of extracted patches served directly as inputs into the following classifiers: CNN.
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
CC Attribution-NoDerivatives 4.0