An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks
The early detection of Diabetic Retinopathy (DR) is critical for diabetics to lower the blindness risks. Many studies represent that Deep Convolutional Neural Network (CNN) based approaches are effective to enable automatic DR detection through classifying retinal images of patients. Such approaches...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9208666/ |
id |
doaj-fab055ca1012423d97f28eb7a44caf5a |
---|---|
record_format |
Article |
spelling |
doaj-fab055ca1012423d97f28eb7a44caf5a2021-03-30T04:49:32ZengIEEEIEEE Access2169-35362020-01-01817855217856210.1109/ACCESS.2020.30277949208666An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural NetworksWanghu Chen0https://orcid.org/0000-0002-9233-7609Bo Yang1Jing Li2Jianwu Wang3https://orcid.org/0000-0002-9933-1170Institute of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaInstitute of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaInstitute of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaDepartment of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, USAThe early detection of Diabetic Retinopathy (DR) is critical for diabetics to lower the blindness risks. Many studies represent that Deep Convolutional Neural Network (CNN) based approaches are effective to enable automatic DR detection through classifying retinal images of patients. Such approaches usually depend on a very large dataset composed of retinal images with predefined classification labels to support their CNN training. However, in some occasions, it is not so easy to get enough well-labelled images to act as model training samples. At the same time, when a CNN becomes deeper, its training will not only take much longer time, but also be more likely to lead to overfitting, especially on a large training dataset. Therefore, it is meaningful to explore a simpler CNN based approach that is still effective on small datasets to classify retinal images. In this paper, an approach to retinal image classification is proposed based on the integration of multi-scale shallow CNNs. Experiments on public datasets show that, on small datasets, the proposed approach can improve the classification accuracy by 3% compared with current representative integrated CNN learning approaches. On the bigger dataset, the proposed approach can improve the classification accuracy by 3% to 9% compared with other representative approaches such as traditional CNN, LCNN and VGG16noFC. The evaluation also represents that, though the classification accuracy of the proposed approach declines by 6% on the smallest dataset containing only 10% samples of the original dataset, its time cost declines to about 30% of that on the original dataset.https://ieeexplore.ieee.org/document/9208666/Convolutional neural networkdiabetic retinopathyimage classificationintegrated learningperformance integration |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wanghu Chen Bo Yang Jing Li Jianwu Wang |
spellingShingle |
Wanghu Chen Bo Yang Jing Li Jianwu Wang An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks IEEE Access Convolutional neural network diabetic retinopathy image classification integrated learning performance integration |
author_facet |
Wanghu Chen Bo Yang Jing Li Jianwu Wang |
author_sort |
Wanghu Chen |
title |
An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks |
title_short |
An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks |
title_full |
An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks |
title_fullStr |
An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks |
title_full_unstemmed |
An Approach to Detecting Diabetic Retinopathy Based on Integrated Shallow Convolutional Neural Networks |
title_sort |
approach to detecting diabetic retinopathy based on integrated shallow convolutional neural networks |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
The early detection of Diabetic Retinopathy (DR) is critical for diabetics to lower the blindness risks. Many studies represent that Deep Convolutional Neural Network (CNN) based approaches are effective to enable automatic DR detection through classifying retinal images of patients. Such approaches usually depend on a very large dataset composed of retinal images with predefined classification labels to support their CNN training. However, in some occasions, it is not so easy to get enough well-labelled images to act as model training samples. At the same time, when a CNN becomes deeper, its training will not only take much longer time, but also be more likely to lead to overfitting, especially on a large training dataset. Therefore, it is meaningful to explore a simpler CNN based approach that is still effective on small datasets to classify retinal images. In this paper, an approach to retinal image classification is proposed based on the integration of multi-scale shallow CNNs. Experiments on public datasets show that, on small datasets, the proposed approach can improve the classification accuracy by 3% compared with current representative integrated CNN learning approaches. On the bigger dataset, the proposed approach can improve the classification accuracy by 3% to 9% compared with other representative approaches such as traditional CNN, LCNN and VGG16noFC. The evaluation also represents that, though the classification accuracy of the proposed approach declines by 6% on the smallest dataset containing only 10% samples of the original dataset, its time cost declines to about 30% of that on the original dataset. |
topic |
Convolutional neural network diabetic retinopathy image classification integrated learning performance integration |
url |
https://ieeexplore.ieee.org/document/9208666/ |
work_keys_str_mv |
AT wanghuchen anapproachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT boyang anapproachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT jingli anapproachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT jianwuwang anapproachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT wanghuchen approachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT boyang approachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT jingli approachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks AT jianwuwang approachtodetectingdiabeticretinopathybasedonintegratedshallowconvolutionalneuralnetworks |
_version_ |
1724181170942377984 |