Computational Model for the Detection of Diabetic Retinopathy in 2-D Color Fundus Retina Scan

Diabetic Retinopathy (DR) is a growing problem in Asian countries. DR accounts for 5% to 7% of all blindness in the entire area. In India, the record of DR-affected patients will reach around 79.4 million by 2030.

The main objective of the investigation is to utilize 2-D colored fundus retina scans to determine if an individual possesses DR or not. In this regard, Engineering-based techniques such as deep learning and neural networks play a methodical role in fighting against this fatal disease.

In this research work, a Computational Model for detecting DR using Convolutional Neural Network (DRCNN) is proposed. This method contrasts the fundus retina scans of the DR-afflicted eye with the usual human eyes. Using CNN and layers like Conv2D, Pooling, Dense, Flatten, and Dropout, the model aids in comprehending the scan's curve and color-based features. For training and error reduction, the Visual Geometry Group (VGG-16) model and Adaptive Moment Estimation Optimizer are utilized.

The variations in a dataset like 50%, 60%, 70%, 80%, and 90% images are reserved for the training phase, and the rest images are reserved for the testing phase. In the proposed model, the VGG-16 model comprises 138M parameters. The accuracy is achieved maximum rate of 90% when the training dataset is reserved at 80%. The model was validated using other datasets.

The suggested contribution to research determines conclusively whether the provided OCT scan utilizes an effective method for detecting DRaffected individuals within just a few moments.