Reliable Estimation of the Number of Compartments in Diffusion MRI

A-priori knowledge of the number of fibers in a voxel is mandatory and crucial when reconstructing multi-fiber voxels in diffusion MRI. Especially for clinical purposes, this estimation needs to be stable, even when only few gradient directions are acquired. In this work, we propose a novel approach to address this problem based on a deep convolutional neural network (CNN), which is able to identify important gradient directions and can be directly trained on real data. To obtain a ground truth using real data, 100 uncorrelated Human Connectome Project datasets are utilized, with a state-of-the-art framework used for generating a relative ground truth. It is shown that this CNN approach outperforms other state-of-the-art machine learning approaches.

Authors and Affiliations

1. Institute of Imaging & Computer Vision, RWTH Aachen University, Aachen, Deutschland

   Simon Koppers, Christoph Haarburger & Dorit Merhof

2. Children’s Hospital of Philadelphia, University of Pennsylvania, Pennsylvania, USA

   J. Christopher Edgar

Corresponding author

Correspondence to Simon Koppers .

Editors and Affiliations

1. Deutsches Krebsforschungszentrum, Juniorgruppe Medizinische Bildverarbeitung, Heidelberg, Germany

   Klaus Hermann Maier-Hein, geb. Fritzsche

2. Uniklinik RWTH Aachen, Institut für Medizinische Informatik, Aachen, Germany

   Thomas Martin Deserno, geb. Lehmann

3. Universität zu Lübeck, Institut für Medizinische Informatik, Lübeck, Germany

   Heinz Handels

4. Charité – Universitätsmedizin Berlin, Institut für Medizinische Informatik, Berlin, Germany

   Thomas Tolxdorff

Reprints and permissions

© 2017 Springer-Verlag GmbH Deutschland

Policies and ethics