Qunatification of Metabolites in MR Spectroscopic Imaging using Machine Learning
This addresses a clinical imaging challenge for medical professionals by improving metabolite quantification in noisy or artifact-laden spectra, though it is incremental as it applies an existing machine learning method to a known bottleneck.
The paper tackles the problem of accurately quantifying metabolites in Magnetic Resonance Spectroscopic Imaging (MRSI) when spectra have poor signal-to-noise ratio or artifacts, by introducing a random forest regression framework that learns from simulated and in-vivo brain spectra, and it shows results comparable to the gold-standard LCModel.
Magnetic Resonance Spectroscopic Imaging (MRSI) is a clinical imaging modality for measuring tissue metabolite levels in-vivo. An accurate estimation of spectral parameters allows for better assessment of spectral quality and metabolite concentration levels. The current gold standard quantification method is the LCModel - a commercial fitting tool. However, this fails for spectra having poor signal-to-noise ratio (SNR) or a large number of artifacts. This paper introduces a framework based on random forest regression for accurate estimation of the output parameters of a model based analysis of MR spectroscopy data. The goal of our proposed framework is to learn the spectral features from a training set comprising of different variations of both simulated and in-vivo brain spectra and then use this learning for the subsequent metabolite quantification. Experiments involve training and testing on simulated and in-vivo human brain spectra. We estimate parameters such as concentration of metabolites and compare our results with that from the LCModel.