Multimodal Prior Appearance Models Based on Regional Clustering of Intensity Profiles

Authors:
François Chung;Hervé Delingette
Affiliations:
Asclepios Research Team, INRIA Sophia-Antipolis, France;Asclepios Research Team, INRIA Sophia-Antipolis, France
Venue:
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Year:
2009

Citing 3
Cited 1

Globally constrained deformable models for 3D object reconstruction

Signal Processing - Special issue on deformable models and techniques for image and signal processing
A New Cluster Validity Index Based on Fuzzy Granulation-degranulation Criteria

ADCOM '07 Proceedings of the 15th International Conference on Advanced Computing and Communications
Statistical Shape Models for 3D Medical Image Segmentation

Statistical Shape Models for 3D Medical Image Segmentation

Regional appearance modeling based on the clustering of intensity profiles

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Model-based image segmentation requires prior information about the appearance of a structure in the image. Instead of relying on Principal Component Analysis such as in Statistical Appearance Models, we propose a method based on a regional clustering of intensity profiles that does not rely on an accurate pointwise registration. Our method is built upon the Expectation-Maximization algorithm with regularized covariance matrices and includes spatial regularization. The number of appearance regions is determined by a novel model order selection criterion. The prior is described on a reference mesh where each vertex has a probability to belong to several intensity profile classes.