Skip navigation
Skip navigation

Texture analysis of the 3D collagen network and automatic classification of the physiology of articular cartilage

Duan, Xiaojuan; Wu, Jianping; Swift, Benjamin; Kirk, Thomas Brett

Description

A close relationship has been found between the 3D collagen structure and physiological condition of articular cartilage (AC). Studying the 3D collagen network in AC offers a way to determine the condition of the cartilage. However, traditional qualitative studies are time consuming and subjective. This study aims to develop a computer vision-based classifier to automatically determine the condition of AC tissue based on the structural characteristics of the collagen network. Texture analysis...[Show more]

dc.contributor.authorDuan, Xiaojuan
dc.contributor.authorWu, Jianping
dc.contributor.authorSwift, Benjamin
dc.contributor.authorKirk, Thomas Brett
dc.date.accessioned2015-12-13T22:34:45Z
dc.identifier.issn1025-5842
dc.identifier.urihttp://hdl.handle.net/1885/76266
dc.description.abstractA close relationship has been found between the 3D collagen structure and physiological condition of articular cartilage (AC). Studying the 3D collagen network in AC offers a way to determine the condition of the cartilage. However, traditional qualitative studies are time consuming and subjective. This study aims to develop a computer vision-based classifier to automatically determine the condition of AC tissue based on the structural characteristics of the collagen network. Texture analysis was applied to quantitatively characterise the 3D collagen structure in normal (International Cartilage Repair Society, ICRS, grade 0), aged (ICRS grade 1) and osteoarthritic cartilages (ICRS grade 2). Principle component techniques and linear discriminant analysis were then used to classify the microstructural characteristics of the 3D collagen meshwork and the condition of the AC. The 3D collagen meshwork in the three physiological condition groups displayed distinctive characteristics. Texture analysis indicated a significant difference in the mean texture parameters of the 3D collagen network between groups. The principle component and linear discriminant analysis of the texture data allowed for the development of a classifier for identifying the physiological status of the AC with an expected prediction error of 4.23%. An automatic image analysis classifier has been developed to predict the physiological condition of AC (from ICRS grade 0 to 2) based on texture data from the 3D collagen network in the tissue.
dc.publisherCarfax Publishing, Taylor & Francis Group
dc.sourceComputer Methods in Biomechanics and Biomedical Engineering
dc.titleTexture analysis of the 3D collagen network and automatic classification of the physiology of articular cartilage
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume18
dc.date.issued2015
local.identifier.absfor090300 - BIOMEDICAL ENGINEERING
local.identifier.ariespublicationU3488905xPUB5109
local.type.statusPublished Version
local.contributor.affiliationDuan, Xiaojuan, University of Western Australia
local.contributor.affiliationWu, Jianping, Curtin University
local.contributor.affiliationSwift, Benjamin, College of Engineering and Computer Science, ANU
local.contributor.affiliationKirk, Thomas Brett, Curtin University
local.description.embargo2037-12-31
local.bibliographicCitation.issue9
local.bibliographicCitation.startpage931
local.bibliographicCitation.lastpage943
local.identifier.doi10.1080/10255842.2013.864284
dc.date.updated2015-12-11T09:23:53Z
local.identifier.scopusID2-s2.0-84918538049
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Duan_Texture_analysis_of_the_3D_2015.pdf1.18 MBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator