Multi-Class Wound Classification via High and Low-Frequency Guidance Network
Wound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfo...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Bioengineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5354/10/12/1385 |
_version_ | 1797381958844547072 |
---|---|
author | Xiuwen Guo Weichao Yi Liquan Dong Lingqin Kong Ming Liu Yuejin Zhao Mei Hui Xuhong Chu |
author_facet | Xiuwen Guo Weichao Yi Liquan Dong Lingqin Kong Ming Liu Yuejin Zhao Mei Hui Xuhong Chu |
author_sort | Xiuwen Guo |
collection | DOAJ |
description | Wound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfortunately, it is still challenging to classify multiple wound types due to the complexity and variety of wound images. Existing CNNs usually extract high- and low-frequency features at the same convolutional layer, which inevitably causes information loss and further affects the accuracy of classification. To this end, we propose a novel High and Low-frequency Guidance Network (HLG-Net) for multi-class wound classification. To be specific, HLG-Net contains two branches: High-Frequency Network (HF-Net) and Low-Frequency Network (LF-Net). We employ pre-trained models ResNet and Res2Net as the feature backbone of the HF-Net, which makes the network capture the high-frequency details and texture information of wound images. To extract much low-frequency information, we utilize a Multi-Stream Dilation Convolution Residual Block (MSDCRB) as the backbone of the LF-Net. Moreover, a fusion module is proposed to fully explore informative features at the end of these two separate feature extraction branches, and obtain the final classification result. Extensive experiments demonstrate that HLG-Net can achieve maximum accuracy of 98.00%, 92.11%, and 82.61% in two-class, three-class, and four-class wound image classifications, respectively, which outperforms the previous state-of-the-art methods. |
first_indexed | 2024-03-08T20:59:35Z |
format | Article |
id | doaj.art-4bfca37116e1427b8c9a9f676f14936f |
institution | Directory Open Access Journal |
issn | 2306-5354 |
language | English |
last_indexed | 2024-03-08T20:59:35Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Bioengineering |
spelling | doaj.art-4bfca37116e1427b8c9a9f676f14936f2023-12-22T13:54:06ZengMDPI AGBioengineering2306-53542023-12-011012138510.3390/bioengineering10121385Multi-Class Wound Classification via High and Low-Frequency Guidance NetworkXiuwen Guo0Weichao Yi1Liquan Dong2Lingqin Kong3Ming Liu4Yuejin Zhao5Mei Hui6Xuhong Chu7School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaWound image classification is a crucial preprocessing step to many intelligent medical systems, e.g., online diagnosis and smart medical. Recently, Convolutional Neural Network (CNN) has been widely applied to the classification of wound images and obtained promising performance to some extent. Unfortunately, it is still challenging to classify multiple wound types due to the complexity and variety of wound images. Existing CNNs usually extract high- and low-frequency features at the same convolutional layer, which inevitably causes information loss and further affects the accuracy of classification. To this end, we propose a novel High and Low-frequency Guidance Network (HLG-Net) for multi-class wound classification. To be specific, HLG-Net contains two branches: High-Frequency Network (HF-Net) and Low-Frequency Network (LF-Net). We employ pre-trained models ResNet and Res2Net as the feature backbone of the HF-Net, which makes the network capture the high-frequency details and texture information of wound images. To extract much low-frequency information, we utilize a Multi-Stream Dilation Convolution Residual Block (MSDCRB) as the backbone of the LF-Net. Moreover, a fusion module is proposed to fully explore informative features at the end of these two separate feature extraction branches, and obtain the final classification result. Extensive experiments demonstrate that HLG-Net can achieve maximum accuracy of 98.00%, 92.11%, and 82.61% in two-class, three-class, and four-class wound image classifications, respectively, which outperforms the previous state-of-the-art methods.https://www.mdpi.com/2306-5354/10/12/1385multi-class wound classificationhigh and low-frequency informationdeep learningtwo-branch networktransfer learning |
spellingShingle | Xiuwen Guo Weichao Yi Liquan Dong Lingqin Kong Ming Liu Yuejin Zhao Mei Hui Xuhong Chu Multi-Class Wound Classification via High and Low-Frequency Guidance Network Bioengineering multi-class wound classification high and low-frequency information deep learning two-branch network transfer learning |
title | Multi-Class Wound Classification via High and Low-Frequency Guidance Network |
title_full | Multi-Class Wound Classification via High and Low-Frequency Guidance Network |
title_fullStr | Multi-Class Wound Classification via High and Low-Frequency Guidance Network |
title_full_unstemmed | Multi-Class Wound Classification via High and Low-Frequency Guidance Network |
title_short | Multi-Class Wound Classification via High and Low-Frequency Guidance Network |
title_sort | multi class wound classification via high and low frequency guidance network |
topic | multi-class wound classification high and low-frequency information deep learning two-branch network transfer learning |
url | https://www.mdpi.com/2306-5354/10/12/1385 |
work_keys_str_mv | AT xiuwenguo multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT weichaoyi multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT liquandong multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT lingqinkong multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT mingliu multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT yuejinzhao multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT meihui multiclasswoundclassificationviahighandlowfrequencyguidancenetwork AT xuhongchu multiclasswoundclassificationviahighandlowfrequencyguidancenetwork |