Shape-Constrained Automatic Segmentation of the Liver Based on a Heuristic Intensity Model

Dagmar Kainmueller, Thomas Lange, Hans Lamecker

September, 2007

Abstract

We present a fully automatic 3D segmentation method forthe liver from contrast-enhanced CT data. It is based on a combinationof a constrained free-form and statistical deformable model. The adap-tation of the model to the image data is performed according to a simplemodel of the typical intensity distribution around the liver boundary andneighboring anatomical structures, considering the potential presence oftumors in the liver. All parameters of the deformation as well as theinitial positioning of the model in the data are estimated automatically.

Type

Conference paper

Publication

Proc. MICCAI Workshop on 3D Segmentation in the Clinic: A Grand Challenge (T. Heimann at al., eds.), pp. 109-116, 2007

This work won the 2007 MICCAI 3D Segmentation Challenge in the category “Automatic Liver Segmentation” (see results).

Shape-Constrained Automatic Segmentation of the Liver Based on a Heuristic Intensity Model

Abstract

Hans Lamecker

Director, Software Development