Semiblind Spectral Factorization Approach for Magnetic Resonance Spectroscopy Quantification

An observed magnetic resonance (MR) spectrum is composed of a set of metabolites spectrum, baseline, and noise. Quantification of metabolites of interest in the MR spectrum provides great opportunity for early diagnosis of dangerous disease such as brain tumors. In this paper, a novel spectral factorization approach based on singular spectrum analysis (SSA) is proposed to quantify magnetic resonance spectroscopy (MRS). In addition, baseline removal is performed in this study. The proposed method is a semiblind spectral factorization algorithm that jointly uses observed signal and prior knowledge about metabolites of interest to improve metabolite separation. In order to incorporate prior knowledge about metabolites of interest, a new covariance matrix is suggested that exploits correlation between the observed nuclear magnetic resonance signal and prior knowledge. The objectives of the proposed method are 1) removing baseline in frequency domain using SSA; 2) extracting the underlying components of MRS signal based on the suggested novel covariance matrix; and 3) reconstructing metabolite of interest by combining some of the extracted components using a novel cost function. Performance of the proposed method is evaluated using both synthetic and real MRS signals. The obtained results show the effectiveness of the proposed technique to accurately remove baseline and extract metabolites of MRS signal.