A Random Riemannian Metric for Probabilistic Shortest-Path Tractography

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

doi:10.1007/978-3-319-24553-9_73

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 proceeding › Article in proceedings › Research › peer-review

584 Downloads (Orbit)

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 language	English
Title of host publication	Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 : Part 1
Editors	Nassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi
Publisher	Springer
Publication date	2015
Pages	597-604
ISBN (Print)	978-3-319-24552-2
ISBN (Electronic)	978-3-319-24553-9
DOIs	https://doi.org/10.1007/978-3-319-24553-9_73
Publication status	Published - 2015
Event	18th International Conference on Medical Image Computing and Computer-Assisted Intervention - Munich, Germany Duration: 5 Oct 2015 → 9 Oct 2015 Conference number: 18 http://www.miccai2015.org/

Conference

Conference	18th International Conference on Medical Image Computing and Computer-Assisted Intervention
Number	18
Country/Territory	Germany
City	Munich
Period	05/10/2015 → 09/10/2015
Internet address	http://www.miccai2015.org/

Series	Lecture Notes in Computer Science
Volume	9349
ISSN	0302-9743

Access to Document

10.1007/978-3-319-24553-9_73

MICCAI2015Accepted author manuscript, 1.81 MB

OpenUrl availability

Full text

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. https://doi.org/10.1007/978-3-319-24553-9_73

Hauberg, Søren ; Schober, Michael ; Liptrot, Matthew George et al. / A Random Riemannian Metric for Probabilistic Shortest-Path Tractography. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: Part 1. editor / Nassir Navab ; Joachim Hornegger ; William M. Wells ; Alejandro F. Frangi. Springer, 2015. pp. 597-604 (Lecture Notes in Computer Science, Vol. 9349).

@inproceedings{6b296227e439476abbcc5e15ea19db58,

title = "A Random Riemannian Metric for Probabilistic Shortest-Path Tractography",

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.",

author = "S{\o}ren Hauberg and Michael Schober and Liptrot, \{Matthew George\} and Philipp Hennig and Aasa Feragen",

year = "2015",

doi = "10.1007/978-3-319-24553-9\_73",

language = "English",

isbn = "978-3-319-24552-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "597--604",

editor = "Navab, \{Nassir \} and Hornegger, \{Joachim \} and Wells, \{William M. \} and Frangi, \{Alejandro F. \}",

booktitle = "Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015",

note = "18th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2015 ; Conference date: 05-10-2015 Through 09-10-2015",

url = "http://www.miccai2015.org/",

}

Hauberg, S, Schober, M, Liptrot, MG, Hennig, P & Feragen, A 2015, A Random Riemannian Metric for Probabilistic Shortest-Path Tractography. in N Navab, J Hornegger, WM Wells & AF Frangi (eds), Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: Part 1. Springer, Lecture Notes in Computer Science, vol. 9349, pp. 597-604, 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 05/10/2015. https://doi.org/10.1007/978-3-319-24553-9_73

A Random Riemannian Metric for Probabilistic Shortest-Path Tractography. / Hauberg, Søren; Schober, Michael; Liptrot, Matthew George et al.
Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: Part 1. ed. / Nassir Navab; Joachim Hornegger; William M. Wells; Alejandro F. Frangi. Springer, 2015. p. 597-604 (Lecture Notes in Computer Science, Vol. 9349).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A Random Riemannian Metric for Probabilistic Shortest-Path Tractography

AU - Hauberg, Søren

AU - Schober, Michael

AU - Liptrot, Matthew George

AU - Hennig, Philipp

AU - Feragen, Aasa

N1 - Conference code: 18

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-24553-9_73

DO - 10.1007/978-3-319-24553-9_73

M3 - Article in proceedings

SN - 978-3-319-24552-2

T3 - Lecture Notes in Computer Science

SP - 597

EP - 604

BT - Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015

A2 - Navab, Nassir

A2 - Hornegger, Joachim

A2 - Wells, William M.

A2 - Frangi, Alejandro F.

PB - Springer

T2 - 18th International Conference on Medical Image Computing and Computer-Assisted Intervention

Y2 - 5 October 2015 through 9 October 2015

ER -

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

A Random Riemannian Metric for Probabilistic Shortest-Path Tractography

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this