TY - GEN
T1 - Sparse representation for white matter fiber compression and calculation of inter-fiber similarity
AU - Moreno, Gali Zimmerman
AU - Alexandroni, Guy
AU - Sochen, Nir
AU - Greenspan, Hayit
N1 - Publisher Copyright:
© Springer International Publishing AG 2017.
PY - 2017
Y1 - 2017
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85019741343&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-54130-3_11
DO - 10.1007/978-3-319-54130-3_11
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85019741343
SN - 9783319541297
T3 - Mathematics and Visualization
SP - 133
EP - 143
BT - Computational Diffusion MRI - MICCAI Workshop
A2 - Fuster, Andrea
A2 - Rathi, Yogesh
A2 - Reisert, Marco
A2 - Kaden, Enrico
A2 - Ghosh, Aurobrata
PB - Springer Heidelberg
T2 - MICCAI Workshop on Computational Diffusion MRI, CDMRI 2016
Y2 - 17 October 2016 through 21 October 2016
ER -