Assessment of Rotationally-Invariant Clustering Using Streamlet Tractography

Matthew George Liptrot, François Lauze

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


We present a novel visualisation-based strategy for the assessment of a recently proposed clustering technique for raw DWI volumes which derives rotationally-invariant metrics to classify voxels. The validity of the division of all brain tissue voxels into such classes was assessed using the recently developed streamlets visualisation technique, which aims to represent brain fibres by collections of many short streamlines. Under the assumption that streamlines seeded in a cluster should stay within it, we were able to assess how well perceptual tracing could occur across the boundaries of the clusters.
Original languageEnglish
Title of host publicationProceedings of the ISMRM 24th Annual Meeting (2016)
Number of pages4
Publication date2016
Publication statusPublished - 2016
EventISMRM 24th Annual Meeting & Exhibition - , Singapore
Duration: 7 May 201613 May 2016
Conference number: 24


ConferenceISMRM 24th Annual Meeting & Exhibition


Dive into the research topics of 'Assessment of Rotationally-Invariant Clustering Using Streamlet Tractography'. Together they form a unique fingerprint.

Cite this