Three-dimensional segmentation of brain aneurysms in CTA using non-parametric region-based information and implicit deformable models: Method and evaluation

Knowledge of brain aneurysm dimensions is essential in minimally invasive surgical interventions using Guglielmi Detachable Coils. These parameters are obtained in clinical routine using 2D maximum intensity projection images. Automated quantification of the three dimensional structure of aneurysms directly from the 3D data set may be used to provide accurate and objective measurements of the clinically relevant parameters. In this paper we present an algorithm devised for the segmentation of brain aneurysms based on implicit deformable models combined with non-parametric region-based information. This work also presents the evaluation of the method in a clinical data base of 39 cases.

Duke Scholars

Author Guillermo Sapiro Electrical and Computer Engineering