Meeting Banner
Abstract #3852

Direct Estimation of Model Parameters in MR Spectroscopic Imaging using Deep Neural Networks

Dhritiman Das1,2, Eduardo Coello2,3, Anjany Sekuboyina1,4, Rolf F Schulte2, and Bjoern H Menze1

1Department of Computer Science, Technical University of Munich, Munich, Germany, 2GE Healthcare, Munich, Germany, 3Department of Physics, Technical University of Munich, Munich, Germany, 4Klinikum rechts der Isar, Munich, Germany

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.

Join Here