Cargando…

Classification of Diabetic Foot Ulcers Using Class Knowledge Banks

Diabetic foot ulcers (DFUs) are one of the most common complications of diabetes. Identifying the presence of infection and ischemia in DFU is important for ulcer examination and treatment planning. Recently, the computerized classification of infection and ischaemia of DFU based on deep learning me...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Yi, Han, Kang, Zhou, Yongming, Wu, Jian, Xie, Xin, Xiang, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8918844/
https://www.ncbi.nlm.nih.gov/pubmed/35295708
http://dx.doi.org/10.3389/fbioe.2021.811028
_version_ 1784668816402284544
author Xu, Yi
Han, Kang
Zhou, Yongming
Wu, Jian
Xie, Xin
Xiang, Wei
author_facet Xu, Yi
Han, Kang
Zhou, Yongming
Wu, Jian
Xie, Xin
Xiang, Wei
author_sort Xu, Yi
collection PubMed
description Diabetic foot ulcers (DFUs) are one of the most common complications of diabetes. Identifying the presence of infection and ischemia in DFU is important for ulcer examination and treatment planning. Recently, the computerized classification of infection and ischaemia of DFU based on deep learning methods has shown promising performance. Most state-of-the-art DFU image classification methods employ deep neural networks, especially convolutional neural networks, to extract discriminative features, and predict class probabilities from the extracted features by fully connected neural networks. In the testing, the prediction depends on an individual input image and trained parameters, where knowledge in the training data is not explicitly utilized. To better utilize the knowledge in the training data, we propose class knowledge banks (CKBs) consisting of trainable units that can effectively extract and represent class knowledge. Each unit in a CKB is used to compute similarity with a representation extracted from an input image. The averaged similarity between units in the CKB and the representation can be regarded as the logit of the considered input. In this way, the prediction depends not only on input images and trained parameters in networks but the class knowledge extracted from the training data and stored in the CKBs. Experimental results show that the proposed method can effectively improve the performance of DFU infection and ischaemia classifications.
format Online
Article
Text
id pubmed-8918844
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-89188442022-03-15 Classification of Diabetic Foot Ulcers Using Class Knowledge Banks Xu, Yi Han, Kang Zhou, Yongming Wu, Jian Xie, Xin Xiang, Wei Front Bioeng Biotechnol Bioengineering and Biotechnology Diabetic foot ulcers (DFUs) are one of the most common complications of diabetes. Identifying the presence of infection and ischemia in DFU is important for ulcer examination and treatment planning. Recently, the computerized classification of infection and ischaemia of DFU based on deep learning methods has shown promising performance. Most state-of-the-art DFU image classification methods employ deep neural networks, especially convolutional neural networks, to extract discriminative features, and predict class probabilities from the extracted features by fully connected neural networks. In the testing, the prediction depends on an individual input image and trained parameters, where knowledge in the training data is not explicitly utilized. To better utilize the knowledge in the training data, we propose class knowledge banks (CKBs) consisting of trainable units that can effectively extract and represent class knowledge. Each unit in a CKB is used to compute similarity with a representation extracted from an input image. The averaged similarity between units in the CKB and the representation can be regarded as the logit of the considered input. In this way, the prediction depends not only on input images and trained parameters in networks but the class knowledge extracted from the training data and stored in the CKBs. Experimental results show that the proposed method can effectively improve the performance of DFU infection and ischaemia classifications. Frontiers Media S.A. 2022-02-28 /pmc/articles/PMC8918844/ /pubmed/35295708 http://dx.doi.org/10.3389/fbioe.2021.811028 Text en Copyright © 2022 Xu, Han, Zhou, Wu, Xie and Xiang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Bioengineering and Biotechnology
Xu, Yi
Han, Kang
Zhou, Yongming
Wu, Jian
Xie, Xin
Xiang, Wei
Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title_full Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title_fullStr Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title_full_unstemmed Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title_short Classification of Diabetic Foot Ulcers Using Class Knowledge Banks
title_sort classification of diabetic foot ulcers using class knowledge banks
topic Bioengineering and Biotechnology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8918844/
https://www.ncbi.nlm.nih.gov/pubmed/35295708
http://dx.doi.org/10.3389/fbioe.2021.811028
work_keys_str_mv AT xuyi classificationofdiabeticfootulcersusingclassknowledgebanks
AT hankang classificationofdiabeticfootulcersusingclassknowledgebanks
AT zhouyongming classificationofdiabeticfootulcersusingclassknowledgebanks
AT wujian classificationofdiabeticfootulcersusingclassknowledgebanks
AT xiexin classificationofdiabeticfootulcersusingclassknowledgebanks
AT xiangwei classificationofdiabeticfootulcersusingclassknowledgebanks