Next: Text Index Contents: Conference Page

Hybrid Segmentation of the Visible Human Data

C. Imielinska, Ph.D.⁽¹⁾, D. Metaxas, Ph.D.⁽²⁾, J. Udupa, Ph.D.⁽³⁾, Yinpeng Jin, M.S.⁽⁴⁾, Ting Cheng, M.S.⁽²⁾

⁽¹⁾ College of Physicians and Surgeons, Office of Scholarly Resources Office of Scholarly Resources and Dept. of Computer Science, Columbia University
⁽²⁾ Dept. of Computer and Information Science, University of Pennsylvania
⁽³⁾ Medical Image Processing Group, Dept. of Radiology, University of Pennsylvania
⁽⁴⁾ Department of Biomedical Engineering, Columbia University ci42@columbia.edu

Abstract
In this paper we develop and test new hybrid methods for segmenting the Visible Human color cryosection and radiological (patient) data (e.g. CT, MRI, PET). The novelty stems from the integration of region-based and deformable model-based segmentation methods with a variety of region-based and statistical methods which aims toward the development of segmentation methods that yield high precision, accuracy and efficiency. This is a collaborative project between the University of Pennsylvania and Columbia University, a part of a larger effort to provide a fully implemented and tested Visible Human Project Segmentation and Registration Toolkit (Insight).

Keywords: Boundary-based segmentation, deformable model segmentation, hybrid method segmentation, region-based segmentation, segmentation, Vesalius^™ Project, visualization.

Table of Contents

Text index
Image index
References
.PDF Version

Next: Text Index Contents: Conference Page

Office of High Performance Computing and Communications
Lister Hill National Center for Biomedical Communications
U.S. National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894
National Institutes of Health
Department of Health & Human Services
Copyright and Privacy Policy
Last updated: 2 July 2001