Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB — retrained AlexNet convolutional neural network

MatLab codes and scripts related to image processing, pre-processing & Training versions of the AlexNet Convolutional Neural Network (NetTransfers I-V)

-The following files and functions are deeper described in the "README.txt" file:

• IMAGE PRE-PROCESSING
  • "Converter_227_final.m"
    • Add a red color filter to grayscale images (grs2rgb by Valeriy Korostyshevskiy)
    • Crop black areas from images
    • Resize images (227x227 pixels)
• IMAGE PROCESSING
  • "CodigoAlterno.m"
    • Code for retraining of convolutional neural networks based on AlexNet pre-trained network
• DATASETS USED IN THIS WORK
• SPECIFICATIONS OF THE DATA USED FOR RETRAINING EACH VERSION OF THE CNN
• FINALL TRAINING VERSIONS OF THE CNN - RELATED TO THE EVALUATION OF EYE DISEASES.

Note: Codes are additionally available on GitHub. On the other hand, the trainings of the convolutional neural network are not subject to changes or modifications (netTransfer I-V) and will only be available in this repository.

PLEASE CITATE AS:

Arias-Serrano I, Velásquez-López PA, Avila-Briones LN et al. Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB — retrained AlexNet convolutional neural network [version 1; peer review: 1 approved with reservations]. F1000Research 2023, 12:14 (https://doi.org/10.12688/f1000research.122288.1)