# US 2014/0191755 A1 · Method and magnetic resonance apparatus for automated analysis of the raw data of a spectrum > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2014/0191755 A1 - Document ID: US20140191755A1 - Status: Published application - Kind: A1 - Application number: 14/146,868 - Filed: 2014-01-03 - Published: 2014-07-10 - Earliest claimed: 2013-01-04 - Assignees: Siemens Aktiengesellschaft - Inventors: Christina Bauer; Martin Berger; Thomas Blum; Christian Schuster - Web page: https://patentgrep.com/patent/US20140191755A1 ## CPC - G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)} - G01R 33/4625: {Processing of acquired signals, e.g. elimination of phase errors, baseline fitting, chemometric analysis} - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) ## Abstract In a method and magnetic resonance apparatus for automating the analysis of MR raw data representing a spectrum, at least one post-processing procedure is applied to the raw data, so as to obtain a processed spectrum. The number of numerical values depicted by the processed spectrum is lowered to a feature vector. The feature vector is allocated to one of numerous groups of known feature vectors. ## Claims ### Claim 1 A computerized method for automating analysis of raw data representing a spectrum, said method comprising: providing said raw data representing a spectrum to a processor and, in said processor, applying at least one post-processing procedure to said raw data, thereby obtaining a processed spectrum; in said processor, reducing a number of numerical values represented by the processed spectrum to a feature vector; in said processor, automatically allocating said feature vector to one group of a plurality of groups of known feature vectors; and in said processor, based on said one group to which said feature vector is allocated, identifying a material from which said spectrum originates and emitting an electronic signal at an output of said processor indicating said material. ### Claim 2 (depends on 1) A method as claimed in claim 1 comprising employing, as said raw data representing said spectrum, raw magnetic resonance data representing said spectrum. ### Claim 3 (depends on 2) A method as claimed in claim 2 comprising employing raw magnetic resonance data representing a proton spectrum. ### Claim 4 (depends on 1) A method as claimed in claim 1 comprising acquiring said raw data representing said spectrum by a data acquisition procedure selected from the group consisting of an SVS measurement and a CSI measurement. ### Claim 5 (depends on 1) A method as claimed in claim 1 comprising determining said feature vector by binning in said processor. ### Claim 6 (depends on 1) A method as claimed in claim 1 comprising determining said feature vector by executing a principal component analysis in said processor. ### Claim 7 (depends on 1) A method as claimed in claim 1 comprising determining said feature vector by executing a procedure in said processor selected from the group consisting of an independency analysis and a Sammon mapping. ### Claim 8 (depends on 1) A method as claimed in claim 1 comprising allocating said feature vector to said one of said groups using a linear classifier. ### Claim 9 (depends on 8) A method as claimed in claim 8 comprising in said processor, using a support vector machine as said linear classifier. ### Claim 10 (depends on 1) A method as claimed in claim 1 comprising allocating said feature vector to said one of said groups using a non-linear classifier. ### Claim 11 (depends on 10) A method as claimed in claim 10 comprising using a support vector machine with an RBF kernel in said processor as said non-linear classifier. ### Claim 12 (depends on 1) A method as claimed in claim 1 comprising implementing a water suppression using a Hankel singular value decomposition in said processor, as said at least one post-processing procedure. ### Claim 13 A magnetic resonance apparatus comprising: a control unit configured to operate said magnetic resonance apparatus to acquire raw MR data representing a spectrum of a material in an examination subject situated in the apparatus; a computerized processor supplied with said raw MR data, said computerized processor being configured to apply at least one post-processing procedure to said raw MR data, thereby obtaining a processed spectrum; said processor being configured to reduce a number of numerical values represented by the processed spectrum to a feature vector; said computerized processor being configured to allocate said feature vector to one group among a plurality of groups of known feature vectors; and said computerized processor being configured to identify said material, based on said one group to which said feature vector is allocated, and to emit an electronic signal at an output of said computerized processor indicating said material.