Using prior shape and intensity profile in medical image segmentation

  • Authors:
  • Yunmei Chen;Feng Huang;Hemant D. Tagare;Murali Rao;David Wilson;Edward A. Geiser

  • Affiliations:
  • -;-;-;-;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this note we present a coupled optimization model forboundary determination. One part of the model incorporatesa prior shape into a geometric active contour modelwith a fixed parameter. The second part determines the'best' parameter used in the first part by maximizing the mutualinformation of the image geometry between the priorand an aligned novel image over all the alignments, thatare the solutions of the first part corresponding to differentparameters. We also present an alternative method, whichgenerates an intensity model formed as the average of a setof aligned training images. Experimental results on cardiacultrasound images are presented. These results indicatethat the proposed model provides close agreement withexpert traced borders, and the parameter determined in thismodel for one image can be used for images with similarproperties. The existence of a solution to the proposed minimizationproblem is also discussed.