Meeting Banner
Abstract #1651

Deep learning with synthetic data for free water elimination in diffusion MRI

Miguel Molina-Romero1,2, Pedro A. Gómez1,2, Shadi Albarqouni1, Jonathan I. Sperl2, Marion I. Menzel2, and Bjoern H. Menze1

1Technical University of Munich, Munich, Germany, 2GE Global Research Europe, Munich, Germany

Diffusion metrics are typically biased by Cerebrospinal fluid (CSF) contamination. In this work, we present a deep learning based solution to remove the CSF contribution. First, we train an artificial neural network (ANN) with synthetic data to estimate the tissue volume fraction. Second, we use the resulting network to predict estimates of the tissue volume fraction for real data, and use them to correct for CSF contamination. Results show corrected CSF contribution which, in turn, indicates that the tissue volume fraction can be estimated using this joint data generation and deep learning approach.

This abstract and the presentation materials are available to members only; a login is required.

Join Here