A multi-resolution watershed-based approach for the segmentation of diffusion tensor images

P. Rodrigues, A.C. Jalba, P. Fillard, Anna Vilanova, B.M. ter Haar Romeny

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

Abstract

The analysis and visualisation of Di usion Tensor Images (DTI) is still a challenge since it is multi-valued and exploratory in nature: tensors, ber tracts, bundles. This quickly leads to clutter problems in visualisation but also in analysis. In this paper, a new framework for the multi-resolution analysis of DTI is proposed. Based on fast and greedy watersheds operating on a multi-scale representation of a DTI image, a hierarchical depiction of a DTI image is determined conveying a global-to-local view of the brous structure of the analysed tissue. The multi-resolution watershed transform provides a coarse to ne partitioning of the data based on the (in)homogeneity of the gradient eld. With a transversal cross scale linking of the basins (regions), a hierarchical representation is established. This framework besides providing a novel hierarchical way to analyse DTI data, allows a simple and interactive segmentation tool where different bundles can be segmented at di erent resolutions. We present preliminary experimental results supporting the validity of the proposed method.
Original languageEnglish
Title of host publication2nd Annual Meeting of the Benelux ISMRM
Number of pages12
Publication statusPublished - 2010
Event2nd Annual Meeting of the Benelux ISMRM - Utrecht, Netherlands
Duration: 18 Jan 201018 Jan 2010

Conference

Conference2nd Annual Meeting of the Benelux ISMRM
CountryNetherlands
CityUtrecht
Period18/01/1018/01/10

    Fingerprint

Cite this