Multi-scale 3-D Deformable Model Segmentation Based on Medial Description

This paper presents a Bayesian multi-scale three dimensional deformable template approach based on a medial representation for the segmentation and shape characterization of anatomical objects in medical imagery. Prior information about the geometry and shape of the anatomical objects under study is incorporated via the construction of exemplary templates. The anatomical variability is accommodated in the Bayesian framework by defining probabilistic transformations on these templates. The modeling approach taken in this paper for building exemplary templates and associated transformations is based on a multi-scale medial representation. The transformations defined in this framework are parameterized directly in terms of natural shape operations, such as thickening and bending, and their location. Quantitative validation results are presented on the automatic segmentation procedure developed for the extraction of the kidney parenchyma-including the renal pelvis-in subjects undergoing ra...

• Type: Conference
• Year: 2001
• Where: IPMI
• Authors: Sarang C. Joshi, Stephen M. Pizer, P. Thomas Fletcher, Andrew Thall, Gregg Tracton
• Keywords: Automatic Segmentation Procedure, Exemplary Templates, IPMI 2001, Medical Imaging, Multi-scale Medial Representation