A Random Riemannian Metric for Probabilistic Shortest-Path Tractography

Søren Hauberg, Michael Schober, Matthew George Liptrot, Philipp Hennig, Aasa Feragen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

310 Downloads (Pure)

Abstract

Shortest-path tractography (SPT) algorithms solve global optimization problems defined from local distance functions. As diffusion MRI data is inherently noisy, so are the voxelwise tensors from which local distances are derived. We extend Riemannian SPT by modeling the stochasticity of the diffusion tensor as a “random Riemannian metric”, where a geodesic is a distribution over tracts. We approximate this distribution with a Gaussian process and present a probabilistic numerics algorithm for computing the geodesic distribution. We demonstrate SPT improvements on data from the Human Connectome Project.
Original languageEnglish
Title of host publicationProceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 : Part 1
EditorsNassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi
PublisherSpringer
Publication date2015
Pages597-604
ISBN (Print)978-3-319-24552-2
ISBN (Electronic)978-3-319-24553-9
DOIs
Publication statusPublished - 2015
Event18th International Conference on Medical Image Computing and Computer-Assisted Intervention - Munich, Germany
Duration: 5 Oct 20159 Oct 2015
Conference number: 18
http://www.miccai2015.org/

Conference

Conference18th International Conference on Medical Image Computing and Computer-Assisted Intervention
Number18
CountryGermany
CityMunich
Period05/10/201509/10/2015
Internet address
SeriesLecture Notes in Computer Science
Volume9349
ISSN0302-9743

Cite this

Hauberg, S., Schober, M., Liptrot, M. G., Hennig, P., & Feragen, A. (2015). A Random Riemannian Metric for Probabilistic Shortest-Path Tractography. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: Part 1 (pp. 597-604). Springer. Lecture Notes in Computer Science, Vol.. 9349 https://doi.org/10.1007/978-3-319-24553-9_73