A Riemannian approach to diffusion tensor images segmentation

Christophe Lenglet, Mikaël Rousson, Rachid Deriche, Olivier Faugeras, Stéphane Lehericy, Kamil Ugurbil

Research output: Contribution to journalConference articlepeer-review


We address the problem of the segmentation of cerebral white matter structures from diffusion tensor images. Our approach is grounded on the theoretically well-founded differential geometrical properties of the space of multivariate normal distributions. We introduce a variational formulation, in the level set framework, to estimate the optimal segmentation according to the following hypothesis: Diffusion tensors exhibit a Gaussian distribution in the different partitions. Moreover, we must respect the geometric constraints imposed by the interfaces existing among the cerebral structures and detected by the gradient of the diffusion tensor image. We validate our algorithm on synthetic data and report interesting results on real datasets. We focus on two structures of the white matter with different properties and respectively known as the corpus callosum and the corticospinal tract.

Original languageEnglish (US)
Pages (from-to)591-602
Number of pages12
JournalLecture Notes in Computer Science
StatePublished - Oct 17 2005
Event19th International Conference on Information Processing in Medical Imaging, IPMI 2005 - Glenwood Springs, CO, United States
Duration: Jul 10 2005Jul 15 2005


Dive into the research topics of 'A Riemannian approach to diffusion tensor images segmentation'. Together they form a unique fingerprint.

Cite this