Meeting Banner
Abstract #4715

Fast and fully automatic differentiation of patients with idiopathic Parkinsonian syndrome and progressive supranuclear palsy using T1-weighted MRI datasets

Nils Daniel Forkert 1 , Jan Sedlacik 2 , and Kai Boelmans 3

1 Department of Radiology, Stanford University, Stanford, CA, United States, 2 Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Germany, 3 Department of Psychiatry and Psychotherapy, University Medical Center Hamburg-Eppendorf, Germany

The differentiation of the progressive nuclear palsy (PSP) from the idiopathic Parkinsonian syndrome (IPS) based on clinical criteria is often difficult and high failure rates have been reported. This work presents a fully automatic method for the automatic differentiation of these two neurological diseases using an atlas-based analysis of high-resolution T1-weighted datasets for regional brain volume determination and subsequent classification using a support vector machine. A first evaluation based on 78 datasets revealed that the proposed method is capable of differentiating IPS (n=57) and PSP patients (n=21) fully automatically in less than 10 minutes and an accuracy of 87.2%.

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

Join Here