Multi-Class Retinal Diseases Detection Using Deep CNN With Minimal Memory Consumption

Machine Learning (ML) such as Artificial Neural Network (ANN), Deep learning, Recurrent Networks (RNN), Alex Net, and ResNet can be considered a broad research direction in the identification classification of critical diseases. CNN its particular variant, usually named U-Net Segmentation, has made revolutionary advancement medical diseases, specifically retinal However, because feature extraction complexity, significant flaw high memory CPU consumption while moving whole map to corresponding decoder. Furthermore, it concatenated unsampled decoder avoids reusing pooling indices. In this work, convolutional neural network (CNN) model is proposed for multi-class problems with efficient use consumption. The been evaluated on standard benchmark dataset Eye having 32 classes From experimental evaluation, concluded that performs better regarding management accuracy. overall comparison performed based precision, recall, accuracy different numbers epochs time by each step. technique achieved an 95% Eye-net dataset.