Quantification of 2D-MRSI Datasets using Random Forest Regression Comparing to Prior Knowledge Based Spectral Fitting applied to  Brain Tumors

Robust spectral quantification is essential in clinical 1H-MRSI. A machine-learning technique to quantify 2D-MRSI data aiming to mimic prior-knowledge fitting of the data of glioma patients at 3T. A Random-Forest Regression method was applied on MRSI-data aiming at obtaining improved starting values for the NLLS-algorithm. Enhanced starting values can bring significant developments in the spectral fit quality in clinical 1H-MRS. Different noise levels were compared in order to verify and improve the fitting. Results indicate that this novel approach could increase fitting precision and eliminate possible errors caused by the using uniform starting values and improve method for MRSI-data quantification.