Figure 1

Steps covered by SC in a pattern recognition system. Most pattern recognition systems can be partitioned into these steps: data acquisition, which in our case obtains either the SV, MV or high resolution MRS data; pre-processing, which converts the raw data in the time domain into processed spectra in the frequency domain with the preferred pre-processing routines and protocols of choice; feature selection/extraction, to measure data vectors properties that are useful for classification; the classification, that uses these features to assign the data vector analysed to a category; and the evaluation, which assesses the model created. SC performs the last three steps (dotted box).