Meeting Banner
Abstract #0695

Automated Segmentation of Cerebellar Nuclei from Ultra-High-Field Quantitative Susceptibility Maps with Multi-Atlas Shape Fusion

Pierre-Louis Bazin1,2,3, Andreas Deistung4, Andreas Schäfer5, Robert Turner1,3, Jürgen Reichenbach4, and Dagmar Timmann6

1Spinoza Centre for Neuroimaging, Amsterdam, Netherlands, 2Netherlands Institute for Neuroscience, Amsterdam, Netherlands, 3Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany, 4Medical Physics Group, Jena University Hospital, Jena, Germany, 5Siemens Healthcare GmbH, Erlangen, Germany, 6Department of Neurology, Essen University Hospital, University of Duisburg-Essen, Essen, Germany

Multi-atlas segmentation techniques fail to properly represent very small nuclei because of their low overlap in the fusion stage. We present a shape modeling approach that recovers more accurately such small structures, which we apply to the segmentation of the deep cerebellar nuclei.

This abstract and the presentation materials are available to members only; a login is required.

Join Here