Tendinopathy discrimination by use of spatial frequency parameters in ultrasound b-mode images

Gregory R. Bashford, Nicholas Tomsen, Shruti Arya, Judith M. Burnfield, Kornelia Kulig

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

The structural characteristics of a healthy tendon are related to the anisotropic speckle patterns observed in ultrasonic images. This speckle orientation is disrupted upon damage to the tendon structure as observed in patients with tendinopathy. Quantification of the structural appearance of tendon shows promise in creating a tool for diagnosing, prognosing, or measuring changes in tendon organization over time. The current work describes a first step taken towards this goal-classification of Achilles tendon images into tendinopathy and control categories. Eight spatial frequency parameters were extracted from regions of interest on tendon images, filtered and classified using linear discriminant analysis. Resulting algorithms had better than 80% accuracy in categorizing tendon image kernels as tendinopathy or control. Tendon images categorized wrongly provided for an interesting clinical association between incorrect classification of tendinopathy kernels as control and the symptom and clinical time history based inclusion criteria. To assess intersession reliability of image acquisition, the first 10 subjects were imaged twice during separate sessions. Test-retest of repeated measures was excellent (r = 0.996, ICC (2,1) = 0.73 with one outlier) indicating a general consistency in imaging techniques.

Original languageEnglish (US)
Article number4497377
Pages (from-to)608-615
Number of pages8
JournalIEEE Transactions on Medical Imaging
Volume27
Issue number5
DOIs
StatePublished - May 1 2008

Fingerprint

Tendinopathy
Tendons
Ultrasonics
Speckle
Achilles Tendon
Discriminant Analysis
Image acquisition
Discriminant analysis
Imaging techniques

Keywords

  • Classifier
  • Image analysis
  • Tendinopathy
  • Tendon
  • Ultrasound

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Tendinopathy discrimination by use of spatial frequency parameters in ultrasound b-mode images. / Bashford, Gregory R.; Tomsen, Nicholas; Arya, Shruti; Burnfield, Judith M.; Kulig, Kornelia.

In: IEEE Transactions on Medical Imaging, Vol. 27, No. 5, 4497377, 01.05.2008, p. 608-615.

Research output: Contribution to journalArticle

@article{9a7171fe760142ec8433a31f975677b5,
title = "Tendinopathy discrimination by use of spatial frequency parameters in ultrasound b-mode images",
abstract = "The structural characteristics of a healthy tendon are related to the anisotropic speckle patterns observed in ultrasonic images. This speckle orientation is disrupted upon damage to the tendon structure as observed in patients with tendinopathy. Quantification of the structural appearance of tendon shows promise in creating a tool for diagnosing, prognosing, or measuring changes in tendon organization over time. The current work describes a first step taken towards this goal-classification of Achilles tendon images into tendinopathy and control categories. Eight spatial frequency parameters were extracted from regions of interest on tendon images, filtered and classified using linear discriminant analysis. Resulting algorithms had better than 80{\%} accuracy in categorizing tendon image kernels as tendinopathy or control. Tendon images categorized wrongly provided for an interesting clinical association between incorrect classification of tendinopathy kernels as control and the symptom and clinical time history based inclusion criteria. To assess intersession reliability of image acquisition, the first 10 subjects were imaged twice during separate sessions. Test-retest of repeated measures was excellent (r = 0.996, ICC (2,1) = 0.73 with one outlier) indicating a general consistency in imaging techniques.",
keywords = "Classifier, Image analysis, Tendinopathy, Tendon, Ultrasound",
author = "Bashford, {Gregory R.} and Nicholas Tomsen and Shruti Arya and Burnfield, {Judith M.} and Kornelia Kulig",
year = "2008",
month = "5",
day = "1",
doi = "10.1109/TMI.2007.912389",
language = "English (US)",
volume = "27",
pages = "608--615",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Tendinopathy discrimination by use of spatial frequency parameters in ultrasound b-mode images

AU - Bashford, Gregory R.

AU - Tomsen, Nicholas

AU - Arya, Shruti

AU - Burnfield, Judith M.

AU - Kulig, Kornelia

PY - 2008/5/1

Y1 - 2008/5/1

N2 - The structural characteristics of a healthy tendon are related to the anisotropic speckle patterns observed in ultrasonic images. This speckle orientation is disrupted upon damage to the tendon structure as observed in patients with tendinopathy. Quantification of the structural appearance of tendon shows promise in creating a tool for diagnosing, prognosing, or measuring changes in tendon organization over time. The current work describes a first step taken towards this goal-classification of Achilles tendon images into tendinopathy and control categories. Eight spatial frequency parameters were extracted from regions of interest on tendon images, filtered and classified using linear discriminant analysis. Resulting algorithms had better than 80% accuracy in categorizing tendon image kernels as tendinopathy or control. Tendon images categorized wrongly provided for an interesting clinical association between incorrect classification of tendinopathy kernels as control and the symptom and clinical time history based inclusion criteria. To assess intersession reliability of image acquisition, the first 10 subjects were imaged twice during separate sessions. Test-retest of repeated measures was excellent (r = 0.996, ICC (2,1) = 0.73 with one outlier) indicating a general consistency in imaging techniques.

AB - The structural characteristics of a healthy tendon are related to the anisotropic speckle patterns observed in ultrasonic images. This speckle orientation is disrupted upon damage to the tendon structure as observed in patients with tendinopathy. Quantification of the structural appearance of tendon shows promise in creating a tool for diagnosing, prognosing, or measuring changes in tendon organization over time. The current work describes a first step taken towards this goal-classification of Achilles tendon images into tendinopathy and control categories. Eight spatial frequency parameters were extracted from regions of interest on tendon images, filtered and classified using linear discriminant analysis. Resulting algorithms had better than 80% accuracy in categorizing tendon image kernels as tendinopathy or control. Tendon images categorized wrongly provided for an interesting clinical association between incorrect classification of tendinopathy kernels as control and the symptom and clinical time history based inclusion criteria. To assess intersession reliability of image acquisition, the first 10 subjects were imaged twice during separate sessions. Test-retest of repeated measures was excellent (r = 0.996, ICC (2,1) = 0.73 with one outlier) indicating a general consistency in imaging techniques.

KW - Classifier

KW - Image analysis

KW - Tendinopathy

KW - Tendon

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=43049157779&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43049157779&partnerID=8YFLogxK

U2 - 10.1109/TMI.2007.912389

DO - 10.1109/TMI.2007.912389

M3 - Article

C2 - 18450534

AN - SCOPUS:43049157779

VL - 27

SP - 608

EP - 615

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 5

M1 - 4497377

ER -