Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy
Diabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the fi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/7/816 |
_version_ | 1797411816189460480 |
---|---|
author | Pingping Liu Xiaokang Yang Baixin Jin Qiuzhan Zhou |
author_facet | Pingping Liu Xiaokang Yang Baixin Jin Qiuzhan Zhou |
author_sort | Pingping Liu |
collection | DOAJ |
description | Diabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the field of medical image processing. Various medical lesion detection systems have been proposed to detect fundus lesions. At present, in the image classification process of diabetic retinopathy, the fine-grained properties of the diseased image are ignored and most of the retinopathy image data sets have serious uneven distribution problems, which limits the ability of the network to predict the classification of lesions to a large extent. We propose a new non-homologous bilinear pooling convolutional neural network model and combine it with the attention mechanism to further improve the network’s ability to extract specific features of the image. The experimental results show that, compared with the most popular fundus image classification models, the network model we proposed can greatly improve the prediction accuracy of the network while maintaining computational efficiency. |
first_indexed | 2024-03-09T04:51:42Z |
format | Article |
id | doaj.art-2425ba526311472ebeec3a500754e3ee |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-09T04:51:42Z |
publishDate | 2021-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-2425ba526311472ebeec3a500754e3ee2023-12-03T13:10:02ZengMDPI AGEntropy1099-43002021-06-0123781610.3390/e23070816Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross EntropyPingping Liu0Xiaokang Yang1Baixin Jin2Qiuzhan Zhou3College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Software, Jilin University, Changchun 130012, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Communication Engineering, Jilin University, Changchun 130012, ChinaDiabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the field of medical image processing. Various medical lesion detection systems have been proposed to detect fundus lesions. At present, in the image classification process of diabetic retinopathy, the fine-grained properties of the diseased image are ignored and most of the retinopathy image data sets have serious uneven distribution problems, which limits the ability of the network to predict the classification of lesions to a large extent. We propose a new non-homologous bilinear pooling convolutional neural network model and combine it with the attention mechanism to further improve the network’s ability to extract specific features of the image. The experimental results show that, compared with the most popular fundus image classification models, the network model we proposed can greatly improve the prediction accuracy of the network while maintaining computational efficiency.https://www.mdpi.com/1099-4300/23/7/816fine-grained image classificationattention mechanismbilinear pooling model |
spellingShingle | Pingping Liu Xiaokang Yang Baixin Jin Qiuzhan Zhou Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy Entropy fine-grained image classification attention mechanism bilinear pooling model |
title | Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy |
title_full | Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy |
title_fullStr | Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy |
title_full_unstemmed | Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy |
title_short | Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy |
title_sort | diabetic retinal grading using attention based bilinear convolutional neural network and complement cross entropy |
topic | fine-grained image classification attention mechanism bilinear pooling model |
url | https://www.mdpi.com/1099-4300/23/7/816 |
work_keys_str_mv | AT pingpingliu diabeticretinalgradingusingattentionbasedbilinearconvolutionalneuralnetworkandcomplementcrossentropy AT xiaokangyang diabeticretinalgradingusingattentionbasedbilinearconvolutionalneuralnetworkandcomplementcrossentropy AT baixinjin diabeticretinalgradingusingattentionbasedbilinearconvolutionalneuralnetworkandcomplementcrossentropy AT qiuzhanzhou diabeticretinalgradingusingattentionbasedbilinearconvolutionalneuralnetworkandcomplementcrossentropy |