Automatic Statistical Shape Model Building from A Priori Information

Jonathan Bailleul (1) , Su Ruan (1) , Daniel Bloyet (2)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 GREYC - Groupe de Recherche en Informatique, Image et Instrumentation de Caen

We propose a method based on a priori knowledge provided by anatomical atlases to build almost automatically a Point Distribution Model of internal brain structures. A training set of 3D shapes is rst constructed by registering an anatomical atlas over a MRI database. Then, the set shape instances are automatically landmarked in a Point Distribution Model optimization framework: according to the recent method developed by Davies et al. [1], a Minimum Description Length principle-based objective function drives the optimization process to the \best" annotation for input training set. Preliminary results of models built for several anatomical structures are encouraging.

Domaines: Traitement des images [eess.IV]

Jonathan Bailleul, Su Ruan, Daniel Bloyet. Automatic Statistical Shape Model Building from A Priori Information. ICISP'03 - IAPR International Conference on Signal and Image Processing, 2003, Agadir, Morocco. pp.540-547. ⟨hal-00965349⟩