CLARET: A Tool for Fully Automated Evaluation of MRSI with Pattern Recognition Methods
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.
Unable to display preview. Download preview PDF.
- 3.Kelm BM, Menze BH, Zechmann CM, et al. Automated Estimation of Tumor Probability in Prostate MRSI: Pattern Recognition vs. Quantification. Magn Reson Med submitted;.Google Scholar
- 4.Menze BH, Lichy MP, Bachert P, et al. Optimal Classification of Long Echo Time In Vivo Magnetic Resonance Spectra in the Detection of Recurrent Brain Tumors. NMR Biomed submitted;.Google Scholar
- 5.Menze BH, Kelm BM, Heck D, et al. Machine based rejection of low-quality spectra, and estimation of tumor probabilities from MRSI. In: Procs BVM; 2006.Google Scholar
- 6.Bendl R, Pross J, Hoess A, et al. VIRTUOS-A Program for Virtual Radiotherapy Simulation and Verification. In: Proc of 11th Int. Conf. on The Use of Computers in Radiation Therapy. A. R. Hounsell u. a. Manchester: North Western Med. Physics Dept.; 1994. p. 226–227.Google Scholar
- 7.Scheenen T, Weiland E, Futterer J, et al. Preliminary Results of IMAPS: An International Multi-Centre Assessment of Prostate MR Spectroscpoy. In: Procs 13th ISMRM, Miami. Springer; 2005.Google Scholar