Automated Framework for Detecting Lumen and Media-Adventitia Borders in Intravascular Ultrasound Images

Ultrasound Med Biol. 2015 Jul;41(7):2001-21. doi: 10.1016/j.ultrasmedbio.2015.03.022. Epub 2015 Apr 25.

Abstract

An automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images was developed on the basis of an adaptive region-growing method and an unsupervised clustering method. To demonstrate the capability of the framework, linear regression, Bland-Altman analysis and distance analysis were used to quantitatively investigate the correlation, agreement and spatial distance, respectively, between our detected borders and manually traced borders in 337 intravascular ultrasound images in vivo acquired from six patients. The results of these investigations revealed good correlation (r = 0.99), good agreement (>96.82% of results within the 95% confidence interval) and small average distance errors (lumen border: 0.08 mm, media-adventitia border: 0.10 mm) between the borders generated by the automated framework and the manual tracing method. The proposed framework was found to be effective in detecting lumen and media-adventitia borders in intravascular ultrasound images, indicating its potential for use in routine studies of vascular disease.

Keywords: Intravascular; Region growing; Ultrasound; Unsupervised clustering.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Coronary Artery Disease / diagnostic imaging*
  • Coronary Vessels / diagnostic imaging*
  • Female
  • Humans
  • Image Enhancement / methods*
  • Image Interpretation, Computer-Assisted / methods*
  • Male
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Ultrasonography, Interventional / methods*
  • Unsupervised Machine Learning