Wear debris from total joint replacements:: evaluation of automated categorisation by scale-invariant feature transforms

David Eckold; Karl Dearn; Duncan Shepherd

doi:10.1080/21681163.2016.1230075

Wear debris from total joint replacements: evaluation of automated categorisation by scale-invariant feature transforms

David Eckold, Karl Dearn, Duncan Shepherd

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

178 Downloads (Pure)

Abstract

Wear debris is a crucial factor in determining the lifespan of a total joint replacement. Not only do particulates between a bearing surfaces increase wear rates through third-body abrasion, but immune reactions can lead to inflammation and osteolysis. In this paper, the use of computer vision to analyse and classify scanning electron microscope images of debris was investigated. UHMWPE debris was generated using an in vitro simulator or a linear tribometer, images were analysed using scale invariant feature transforms and a support vector machine classifier. The accuracy was 77.6% with a receiver operating characteristic area under curve of 92%.

Original language	English
Number of pages	10
Journal	Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Early online date	7 Nov 2016
DOIs	https://doi.org/10.1080/21681163.2016.1230075 https://doi.org/10.1080/21681163.2016.1230075
Publication status	E-pub ahead of print - 7 Nov 2016

Keywords

Total disc arthroplasty;
Polymer wear debris;
SVM;
SIFT;
Machine learning;

Access to Document

Wear debris from total joint replacements evaluation of automated categorisation by scale invariant feature transformsFinal published version, 1.21 MBLicence: Creative Commons: Attribution (CC BY)

http://www.tandfonline.com/action/showCopyRight?scroll=top&doi=10.1080%2F21681163.2016.1230075Licence: Creative Commons: Attribution (CC BY)

1 Citations
1 Article

The evolution of polymer wear debris from total disc arthroplasty
Eckold, D. G., Dearn, K. D. & Shepherd, D. E. T., Mar 2015, In: Biotribology. 1–2, p. 42-50 9 p.
Research output: Contribution to journal › Article › peer-review

Open Access
File
12 Citations (Scopus)

316 Downloads (Pure)

Cite this

Eckold, D., Dearn, K., & Shepherd, D. (2016). Wear debris from total joint replacements: evaluation of automated categorisation by scale-invariant feature transforms. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. Advance online publication. https://doi.org/10.1080/21681163.2016.1230075, https://doi.org/10.1080/21681163.2016.1230075

@article{9a0ae1e0acd842f8a15b2af7ecd1fed3,

title = "Wear debris from total joint replacements:: evaluation of automated categorisation by scale-invariant feature transforms",

abstract = "Wear debris is a crucial factor in determining the lifespan of a total joint replacement. Not only do particulates between a bearing surfaces increase wear rates through third-body abrasion, but immune reactions can lead to inflammation and osteolysis. In this paper, the use of computer vision to analyse and classify scanning electron microscope images of debris was investigated. UHMWPE debris was generated using an in vitro simulator or a linear tribometer, images were analysed using scale invariant feature transforms and a support vector machine classifier. The accuracy was 77.6% with a receiver operating characteristic area under curve of 92%.",

keywords = "Total disc arthroplasty; , Polymer wear debris; , SVM; , SIFT; , Machine learning;",

author = "David Eckold and Karl Dearn and Duncan Shepherd",

year = "2016",

month = nov,

day = "7",

doi = "10.1080/21681163.2016.1230075",

language = "English",

journal = "Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization",

issn = "2168-1163",

publisher = "Taylor & Francis",

}

TY - JOUR

T1 - Wear debris from total joint replacements:

T2 - evaluation of automated categorisation by scale-invariant feature transforms

AU - Eckold, David

AU - Dearn, Karl

AU - Shepherd, Duncan

PY - 2016/11/7

Y1 - 2016/11/7

N2 - Wear debris is a crucial factor in determining the lifespan of a total joint replacement. Not only do particulates between a bearing surfaces increase wear rates through third-body abrasion, but immune reactions can lead to inflammation and osteolysis. In this paper, the use of computer vision to analyse and classify scanning electron microscope images of debris was investigated. UHMWPE debris was generated using an in vitro simulator or a linear tribometer, images were analysed using scale invariant feature transforms and a support vector machine classifier. The accuracy was 77.6% with a receiver operating characteristic area under curve of 92%.

AB - Wear debris is a crucial factor in determining the lifespan of a total joint replacement. Not only do particulates between a bearing surfaces increase wear rates through third-body abrasion, but immune reactions can lead to inflammation and osteolysis. In this paper, the use of computer vision to analyse and classify scanning electron microscope images of debris was investigated. UHMWPE debris was generated using an in vitro simulator or a linear tribometer, images were analysed using scale invariant feature transforms and a support vector machine classifier. The accuracy was 77.6% with a receiver operating characteristic area under curve of 92%.

KW - Total disc arthroplasty;

KW - Polymer wear debris;

KW - SVM;

KW - SIFT;

KW - Machine learning;

U2 - 10.1080/21681163.2016.1230075

DO - 10.1080/21681163.2016.1230075

M3 - Article

SN - 2168-1163

JO - Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization

JF - Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization

ER -

Wear debris from total joint replacements: evaluation of automated categorisation by scale-invariant feature transforms

Abstract

Keywords

Access to Document

Fingerprint

Research output

The evolution of polymer wear debris from total disc arthroplasty

Cite this