Evaluation of a Cardiac Ultrasound Segmentation Algorithm Using a Phantom

  • Authors:

  • Yong Yue;Hemant D. Tagare;Ernest L. Madsen;Gary R. Frank;Maritza A. Hobson

  • Affiliations:

  • Department of Diagnostic Radiology, School of Medicine, Yale University, New Haven, USA CT 06511;Department of Diagnostic Radiology, School of Medicine, Yale University, New Haven, USA CT 06511 and Department of Biomedical Engineering, Yale University, New Haven, CT 06520;Department of Medical Physics, University of Wisconsin-Madison, Madison, USA WI 53706-1532;Department of Medical Physics, University of Wisconsin-Madison, Madison, USA WI 53706-1532;Department of Medical Physics, University of Wisconsin-Madison, Madison, USA WI 53706-1532

  • Venue:
  • MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper evaluates the performance of a level set algorithm for segmenting the endocardium in short-axis ultrasound images. The evaluation is carried out using an anthropomorphic ultrasound phantom. Details of the phantom design, including comparison of the ultrasound parameters with in-vitro measurements, are included.In addition to measuring segmentation accuracy, the effectiveness of the energy minimization scheme is also determined. It is argued that using the phantom along with global minimization algorithms (simulated annealing and random search) makes is possible to assess the minimization strategy.