» Articles » PMID: 35295708

Classification of Diabetic Foot Ulcers Using Class Knowledge Banks

Overview
Date 2022 Mar 17
PMID 35295708
Authors
Affiliations
Soon will be listed here.
Abstract

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.

Citing Articles

Artificial Intelligence Methods for Diagnostic and Decision-Making Assistance in Chronic Wounds: A Systematic Review.

Reifs Jimenez D, Casanova-Lozano L, Grau-Carrion S, Reig-Bolano R J Med Syst. 2025; 49(1):29.

PMID: 39969674 PMC: 11839728. DOI: 10.1007/s10916-025-02153-8.


A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning.

Wang C, Yu Z, Long Z, Zhao H, Wang Z Sci Rep. 2024; 14(1):29877.

PMID: 39622873 PMC: 11612188. DOI: 10.1038/s41598-024-80691-w.


DFUCare: deep learning platform for diabetic foot ulcer detection, analysis, and monitoring.

Sendilraj V, Pilcher W, Choi D, Bhasin A, Bhadada A, Bhadadaa S Front Endocrinol (Lausanne). 2024; 15:1386613.

PMID: 39381435 PMC: 11460545. DOI: 10.3389/fendo.2024.1386613.


E-DFu-Net: An efficient deep convolutional neural network models for Diabetic Foot Ulcer classification.

F Almufadi N, F Alhasson H, S Alharbi S Biomol Biomed. 2024; 25(2):445-460.

PMID: 39319898 PMC: 11734831. DOI: 10.17305/bb.2024.11117.


Classification of Diabetic Foot Ulcers from Images Using Machine Learning Approach.

Almufadi N, F Alhasson H Diagnostics (Basel). 2024; 14(16).

PMID: 39202295 PMC: 11353632. DOI: 10.3390/diagnostics14161807.


References
1.
Veredas F, Mesa H, Morente L . Binary tissue classification on wound images with neural networks and bayesian classifiers. IEEE Trans Med Imaging. 2009; 29(2):410-27. DOI: 10.1109/TMI.2009.2033595. View

2.
Chen T, Liu X, Feng R, Wang W, Yuan C, Lu W . Discriminative Cervical Lesion Detection in Colposcopic Images With Global Class Activation and Local Bin Excitation. IEEE J Biomed Health Inform. 2021; 26(4):1411-1421. DOI: 10.1109/JBHI.2021.3100367. View

3.
Wang Z, Liu Q, Dou Q . Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification. IEEE J Biomed Health Inform. 2020; 24(10):2806-2813. PMC: 8545175. DOI: 10.1109/JBHI.2020.3023246. View

4.
Chen J, Ying H, Liu X, Gu J, Feng R, Chen T . A Transfer Learning Based Super-Resolution Microscopy for Biopsy Slice Images: The Joint Methods Perspective. IEEE/ACM Trans Comput Biol Bioinform. 2020; 18(1):103-113. DOI: 10.1109/TCBB.2020.2991173. View

5.
Wannous H, Lucas Y, Treuillet S . Enhanced assessment of the wound-healing process by accurate multiview tissue classification. IEEE Trans Med Imaging. 2010; 30(2):315-26. DOI: 10.1109/TMI.2010.2077739. View