| | |
Summary: A 3D Statistical Shape Model Of The Pelvic Bone For
Segmentation
Hans Lameckera, Martin Seebaßb, Hans-Christian Hegea, Peter Deuflharda
aZuse Institute, Takustr. 7, 14195 Berlin, Germany;
bIndeed Visual Concepts GmbH, Ihnestr. 23, 14195 Berlin, Germany
ABSTRACT
Statistical models of shape are a promising approach for robust and automatic segmentation of medical image
data. This work describes the construction of a statistical shape model of the pelvic bone. An interactive
approach is proposed for solving the correspondence problem which is able to handle shapes of arbitrary topology,
suitable for the genus 3 surface of the pelvic bone. Moreover it allows to specify corresponding anatomical features
as boundary constraints to the matching process. The model's capability for segmentation was tested on a set of
23 CT data sets. Quantitative results will be presented, showing that the model is well suited for segmentation
purposes.
Keywords: statistical shape models, 3d correspondence problem, model-based segmentation, pelvic bone
1. INTRODUCTION
1.1. Motivation
Hyperthermia is a promising approach in cancer therapy. The method is based on heating up affected tissue
compartments to temperatures above 42 degree Celsius without damaging surrounding tissue compartments. In
regional hyperthermia tumors in the pelvic region are heated using radio waves. Treatment planning consists
of simulating and optimizing the temperature distribution in the patient with the aim of computing optimal
|
