Ultrasound Characterization of Bone Demineralization Using a Support Vector Machine

Max Denis, Leighton Wan, Mostafa Fatemi, Azra Alizad

Research output: Contribution to journalArticle

5 Scopus citations

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

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