Ultrasound Characterization of Bone Demineralization Using a Support Vector Machine

Max Denis, Leighton Wan, Mostafa Fatemi, Azra Alizad

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We propose an ultrasound-guided remote measurement technique, utilizing an acoustic radiation force beam as our excitation source and a receiving hydrophone, to assess non-invasively a bone's mechanical properties. Features, such as velocity, were extracted from the acoustic pressure received from the bone surface. The typical velocity of an intact bone (3540 m/s) was higher in comparison to that of a demineralized bone (2231 m/s). According to the receiver operating characteristic curve, the optimal velocity cutoff value of ≥3096 m/s yields 80% sensitivity and 82.61% specificity between intact and demineralized bone. Utilizing a support vector machine, the hours of bone demineralization were successfully classified with maximum accuracy >80% using 18% training data. The results indicate the potential application of our proposed technique and support vector machine for monitoring bone mechanical properties.

Original languageEnglish (US)
Pages (from-to)714-725
Number of pages12
JournalUltrasound in Medicine and Biology
Volume44
Issue number3
DOIs
StatePublished - Mar 1 2018

Fingerprint

bone demineralization
bones
Bone and Bones
Acoustics
mechanical properties
hydrophones
sound waves
Support Vector Machine
ROC Curve
education
cut-off
receivers
Radiation
acoustics

Keywords

  • Acoustic radiation force
  • Bone
  • Demineralization
  • Quantitative ultrasound
  • Support vector machines

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Biophysics
  • Acoustics and Ultrasonics

Cite this

Ultrasound Characterization of Bone Demineralization Using a Support Vector Machine. / Denis, Max; Wan, Leighton; Fatemi, Mostafa; Alizad, Azra.

In: Ultrasound in Medicine and Biology, Vol. 44, No. 3, 01.03.2018, p. 714-725.

Research output: Contribution to journalArticle

@article{aa1c0327e5a94c7399778cdc546c4fb4,
title = "Ultrasound Characterization of Bone Demineralization Using a Support Vector Machine",
abstract = "We propose an ultrasound-guided remote measurement technique, utilizing an acoustic radiation force beam as our excitation source and a receiving hydrophone, to assess non-invasively a bone's mechanical properties. Features, such as velocity, were extracted from the acoustic pressure received from the bone surface. The typical velocity of an intact bone (3540 m/s) was higher in comparison to that of a demineralized bone (2231 m/s). According to the receiver operating characteristic curve, the optimal velocity cutoff value of ≥3096 m/s yields 80{\%} sensitivity and 82.61{\%} specificity between intact and demineralized bone. Utilizing a support vector machine, the hours of bone demineralization were successfully classified with maximum accuracy >80{\%} using 18{\%} training data. The results indicate the potential application of our proposed technique and support vector machine for monitoring bone mechanical properties.",
keywords = "Acoustic radiation force, Bone, Demineralization, Quantitative ultrasound, Support vector machines",
author = "Max Denis and Leighton Wan and Mostafa Fatemi and Azra Alizad",
year = "2018",
month = "3",
day = "1",
doi = "10.1016/j.ultrasmedbio.2017.11.004",
language = "English (US)",
volume = "44",
pages = "714--725",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "3",

}

TY - JOUR

T1 - Ultrasound Characterization of Bone Demineralization Using a Support Vector Machine

AU - Denis, Max

AU - Wan, Leighton

AU - Fatemi, Mostafa

AU - Alizad, Azra

PY - 2018/3/1

Y1 - 2018/3/1

N2 - We propose an ultrasound-guided remote measurement technique, utilizing an acoustic radiation force beam as our excitation source and a receiving hydrophone, to assess non-invasively a bone's mechanical properties. Features, such as velocity, were extracted from the acoustic pressure received from the bone surface. The typical velocity of an intact bone (3540 m/s) was higher in comparison to that of a demineralized bone (2231 m/s). According to the receiver operating characteristic curve, the optimal velocity cutoff value of ≥3096 m/s yields 80% sensitivity and 82.61% specificity between intact and demineralized bone. Utilizing a support vector machine, the hours of bone demineralization were successfully classified with maximum accuracy >80% using 18% training data. The results indicate the potential application of our proposed technique and support vector machine for monitoring bone mechanical properties.

AB - We propose an ultrasound-guided remote measurement technique, utilizing an acoustic radiation force beam as our excitation source and a receiving hydrophone, to assess non-invasively a bone's mechanical properties. Features, such as velocity, were extracted from the acoustic pressure received from the bone surface. The typical velocity of an intact bone (3540 m/s) was higher in comparison to that of a demineralized bone (2231 m/s). According to the receiver operating characteristic curve, the optimal velocity cutoff value of ≥3096 m/s yields 80% sensitivity and 82.61% specificity between intact and demineralized bone. Utilizing a support vector machine, the hours of bone demineralization were successfully classified with maximum accuracy >80% using 18% training data. The results indicate the potential application of our proposed technique and support vector machine for monitoring bone mechanical properties.

KW - Acoustic radiation force

KW - Bone

KW - Demineralization

KW - Quantitative ultrasound

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85044443968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044443968&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2017.11.004

DO - 10.1016/j.ultrasmedbio.2017.11.004

M3 - Article

VL - 44

SP - 714

EP - 725

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 3

ER -