Sparse representation for white matter fiber compression and calculation of inter-fiber similarity

Gali Zimmerman Moreno*, Guy Alexandroni, Nir Sochen, Hayit Greenspan

*Corresponding author for this work

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

3 Scopus citations

Abstract

Recent years have brought about impressive reconstructions of white matter architecture, due to the advance of increasingly sophisticated MRI based acquisition methods and modeling techniques. These result in extremely large sets of streamelines (fibers) for each subject. The sets require large amount of storage and are often unwieldy and difficult to manipulate and analyze. We propose to use sparse representations for fibers to achieve a more compact representation. We also propose the means for calculating inter-fiber similarities in the compressed space using a measure, which we term: Cosine with Dictionary Similarity Weighting (CWDS). The performance of both sparse representations and CWDS is evaluated on full brain fiber-sets of 15 healthy subjects. The results show that a reconstruction error of slightly below 2 mm is achieved, and that CWDS is highly correlated with the cosine similarity in the original space.

Original languageEnglish
Title of host publicationComputational Diffusion MRI - MICCAI Workshop
EditorsAndrea Fuster, Yogesh Rathi, Marco Reisert, Enrico Kaden, Aurobrata Ghosh
PublisherSpringer Heidelberg
Pages133-143
Number of pages11
ISBN (Print)9783319541297
DOIs
StatePublished - 2017
EventMICCAI Workshop on Computational Diffusion MRI, CDMRI 2016 - Athens, Greece
Duration: 17 Oct 201621 Oct 2016

Publication series

NameMathematics and Visualization
ISSN (Print)1612-3786
ISSN (Electronic)2197-666X

Conference

ConferenceMICCAI Workshop on Computational Diffusion MRI, CDMRI 2016
Country/TerritoryGreece
CityAthens
Period17/10/1621/10/16

Fingerprint

Dive into the research topics of 'Sparse representation for white matter fiber compression and calculation of inter-fiber similarity'. Together they form a unique fingerprint.

Cite this