Interactive Segmentation of 3D Ultrasound Using Deformable Solid Models and Active Contours

This paper presents a prototype segmentation system for three-dimensional ultrasound data. 3D ultrasound is cheap and non-nvasive but the data has a low signal-to-noise ratio and contains artifacts. To overcome these difficulties we have developed a system which uses a prior model, initialised by a clinician, to provide the starting point for a data-driven segmentation algorithm based on active contours. Results are presented showing how the technique can facilitate the segmentation of a gall-bladder.

[1]  Christopher J. Taylor,et al.  Model-Based Interpretation of 3D Medical Images , 1993, BMVC.

[2]  S Revankar,et al.  Supervised interpretation of echocardiograms with a psychological model of expert supervision. , 1995, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[3]  Max A. Viergever,et al.  A discrete dynamic contour model , 1995, IEEE Trans. Medical Imaging.

[4]  Linda G. Shapiro,et al.  Image Segmentation Techniques , 1984, Other Conferences.

[5]  Max A. Viergever,et al.  Evaluation of Segmentation Algorithms for Intravascular Ultrasound Images , 1996, VBC.

[6]  Alex Pentland,et al.  Closed-Form Solutions for Physically Based Shape Modeling and Recognition , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Laurent D. Cohen,et al.  Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  William A. Barrett,et al.  Fast, Accurate, and Reproducible Live-Wire Boundary Extraction , 1996, VBC.