We introduce a deep neural-network framework based on a multilayer perceptron for estimation of the output parameters of a model-based analysis of MR spectroscopy data. Our proposed framework: (1) learns the spectral features from a training set comprising of different variations of synthetic spectra; (2) uses this learning and performs non-linear regression for the subsequent metabolite quantification. Experiments involve training and testing on simulated and in-vivo human brain spectra. We estimate parameters such as metabolite-concentration ratios and compare our results with that from the LCModel.
This abstract and the presentation materials are available to members only; a login is required.