Fast and Accurate Multi-Tissue Deconvolution Using SHORE and H-psd Tensors

Michael Ankele, Lek-Heng Lim, Samuel Gröschel und Thomas Schultz

In proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, 2016

Abstract

We propose a new regularization for spherical deconvolution in diffusion MRI. It is based on observing that higher-order tensor representations of fiber ODFs should be H-psd, i.e., they should have a positive semidefinite (psd) matrix H_T. We show that this constraint is stricter than the currently more widely used non-negativity, and that it can be enforced easily using quadratic cone programming. We demonstrate its use in a multi-tissue deconvolution framework that models the different tissue types in the continuous SHORE basis and can therefore be applied to data with multiple b values that are not organized on shells, such as in Diffusion Spectrum Imaging. Experiments on simulated fiber crossings, data from the Human Connectome Project, and clinical data, demonstrate the improved speed and accuracy of this new method.

Bilder

Zusätzliches Material

Preprint (The definite version is available at www.springerlink.com) (PDF-Dokument, 2.2 MB)

Bibtex

@INPROCEEDINGS{ankele:miccai16,
     author = {Ankele, Michael and Lim, Lek-Heng and Gr{\"o}schel, Samuel and Schultz, Thomas},
      title = {Fast and Accurate Multi-Tissue Deconvolution Using SHORE and H-psd Tensors},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
       year = {2016},
  publisher = {Springer},
       note = {In press.},
   abstract = {We propose a new regularization for spherical deconvolution in diffusion MRI. It is based on
               observing that higher-order tensor representations of fiber ODFs should be H-psd, i.e., they should
               have a positive semidefinite (psd) matrix H_T. We show that this constraint is stricter than the
               currently more widely used non-negativity, and that it can be enforced easily using quadratic cone
               programming. We demonstrate its use in a multi-tissue deconvolution framework that models the
               different tissue types in the continuous SHORE basis and can therefore be applied to data with
               multiple b values that are not organized on shells, such as in Diffusion Spectrum Imaging.
               Experiments on simulated fiber crossings, data from the Human Connectome Project, and clinical data,
               demonstrate the improved speed and accuracy of this new method.}
}