CLARET: A Tool for Fully Automated Evaluation of MRSI with Pattern Recognition Methods

Abstract. Magnetic Resonance Spectroscopic Imaging (MRSI) measures relative concentrations of metabolites in vivo and can thus be used for the diagnosis of certain tumors. We introduce the program CLARET that makes MRSI accessible for clinical routine use. Instead of embarking on an error-prone quantification of metabolites that requires manual checking of the results in many voxels, the program uses pattern recognition methods to directly compute tumor probability maps. Furthermore, non-evaluable signals are identified and masked out. The user can thus save time and concentrate on suspicious regions only.

• Type: Conference
• Year: 2006
• Where: BILDMED
• Authors: B. Michael Kelm, Bjoern H. Menze, T. Neff, Christian M. Zechmann, Fred A. Hamprecht
• Keywords: BILDMED 2006, BILDMED 2007, Clinical Routine Use, Magnetic Resonance Spectroscopic Imaging, Metabolites