Robust Classification Model for Diabetic Retinopathy Based on the Contrastive Learning Method with a Convolutional Neural Network

Diabetic retinopathy is one of the most common microvascular complications of diabetes. Early detection and treatment can effectively reduce the risk. Hence, a robust computer-aided diagnosis model is important. Based on the labeled fundus images, we build a binary classification model based on ResN...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-12, Vol.12 (23), p.12071
Main Authors: Feng, Xinxing, Zhang, Shuai, Xu, Long, Huang, Xin, Chen, Yanyan
Format: Article
Language:English
Subjects:
Artificial intelligence
Classification
Complications
convolutional neural network
Data augmentation
Datasets
Deep learning
Diabetes
Diabetes mellitus
Diabetic retinopathy
diabetic retinopathy classification
Edema
Image classification
Machine learning
Microvasculature
Model accuracy
Model testing
Neural networks
Retinopathy
Risk reduction
supervised contrastive learning
Transfer learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Diabetic retinopathy is one of the most common microvascular complications of diabetes. Early detection and treatment can effectively reduce the risk. Hence, a robust computer-aided diagnosis model is important. Based on the labeled fundus images, we build a binary classification model based on ResNet-18 and transfer learning and, more importantly, improve the robustness of the model through supervised contrastive learning. The model is tested with different learning rates and data augmentation methods. The standard deviations of the multiple test results decrease from 4.11 to 0.15 for different learning rates and from 1.53 to 0.18 for different data augmentation methods. In addition, the supervised contrastive learning method also improves the average accuracy of the model, which increases from 80.7% to 86.5%.
ISSN:2076-3417
2076-3417
DOI:10.3390/app122312071