Share Email Print

Proceedings Paper

Segmentation in virtual colonoscopy using a geometric deformable model
Author(s): Christopher L. Wyatt; Yaorong Ge; David J. Vining M.D.
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The Geometric Deformable Model is developed for accurate colon lumen segmentation as part of an automatic Virtual Colonoscopy system. The deformable model refines the lumen surface found by an automatic seed location and thresholding procedure. The challenges to applying the deformable model are described, showing the definition of the stopping function as the key to accurate segmentation. The limitations of current stopping criteria are examined and a new definition, tailored to the task of colon segmentation, is given. First, a multiscale edge operator is used to locate high confidence boundaries. These boundaries are then integrated into the stopping function using a distance transform. The hypothesis is that the new stopping function results in a more accurate representation of the lumen surface compared to previous monotonic functions of the gradient magnitude. This hypothesis is tested using observer ratings of colon surface fidelity at 100 hundred randomly selected locations in each of four datasets. The results show that the surfaces determined by the modified deformable model better represent the lumen surface overall.

Paper Details

Date Published: 30 April 2004
PDF: 12 pages
Proc. SPIE 5369, Medical Imaging 2004: Physiology, Function, and Structure from Medical Images, (30 April 2004); doi: 10.1117/12.535238
Show Author Affiliations
Christopher L. Wyatt, Virginia Polytechnic Institute and State Univ. (United States)
Yaorong Ge, PointDx, Inc. (United States)
David J. Vining M.D., PointDx, Inc. (United States)

Published in SPIE Proceedings Vol. 5369:
Medical Imaging 2004: Physiology, Function, and Structure from Medical Images
Amir A. Amini; Armando Manduca, Editor(s)

© SPIE. Terms of Use
Back to Top