Resumen
One of the main applications of in vivo magnetic resonance spectroscopy (MRS) is in the non-invasive monitoring of the metabolic pattern of brain tumors. MRS comes in two basic modalities, single-voxel (SV), from which the signal is obtained, and multivoxel (MV), in which one or more contiguous grids of SVs are acquired. The purpose of our proof-of-concept study was to test whether it would be possible to train machine learning models using SV data at 1.5T, and test them with MV 3T data from independent patients, obtaining color-coded images of pathology (nosological images) to help radiologists in their preoperative evaluation of patients. With sequential forward feature selection followed by linear discriminant analysis, we obtained AUCs = 0.95 (meningioma), 0.89 (aggressive), 0.82 (low-grade glioma), and 0.82 (normal brain) in the MV test set.