François Chung, Ph.D.
MICCAI 2009 – Conference

MICCAI 2009 – Conference proceeding


François Chung, Hervé Delingette; Multimodal prior appearance models based on regional clustering of intensity profiles; MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention, London, 2009.


Model-based image segmentation requires prior information about the appearance of a structure in the image. Instead of relying on Principal Component Analysis (PCA) such as in Statistical Appearance Models (SAMs), 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 (EM) 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.



Related articles

Multimodal prior (INRIA project)
3D Anatomical Human (INRIA project)

Learn more

MICCAI – Medical Image Computing and Computer Assisted Intervention