Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images

Mika Pollari; Tuomas Neuvonen; Mikko Lilja; Jyrki Lötjönen

doi:10.1109/ISBI.2007.356965

Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images

Mika Pollari, Tuomas Neuvonen, Mikko Lilja, Jyrki Lötjönen

VTT Technical Research Centre of Finland

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

3 Citations (Scopus)

Abstract

Deriving an accurate cost function for tensor valued data has been one of the main difficulties in diffusion tensor image (DTI) registration. In this work, we evaluate and compare five voxel similarity measures: Euclidean distance (ED), Log-Euclidean distance (LOG), distance based on diffusion profiles (DP), diffusion mode based similarity (MBS), and multichannel version of sum of squared differences (SSD). In evaluation we used an optimization-independent evaluation protocol to assess the capture range, the number of local minima, and cyclic registrations to evaluate consistency. Statistically significant differences were observed: DP and MBS were found to be the most consistent similarity measures, ED had the least number of local minima, and SSD was inferior to other similarity measures in all evaluations.

Original language	English
Title of host publication	2007 4th IEEE International Symposium on Biomedical Imaging:
Subtitle of host publication	From Nano to Macro
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	768-771
ISBN (Electronic)	978-1-4244-0672-2
ISBN (Print)	978-1-4244-0671-5
DOIs	https://doi.org/10.1109/ISBI.2007.356965
Publication status	Published - 2007
MoE publication type	A4 Article in a conference publication
Event	4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2007 - Arlington, VA, United States Duration: 12 Apr 2007 → 15 Apr 2007

Conference

Conference	4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2007
Country/Territory	United States
City	Arlington, VA
Period	12/04/07 → 15/04/07

Keywords

Image processing
Image registration

Access to Document

10.1109/ISBI.2007.356965

Cite this

@inproceedings{4ba035abcdd84597be308236aba4e175,

title = "Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images",

abstract = "Deriving an accurate cost function for tensor valued data has been one of the main difficulties in diffusion tensor image (DTI) registration. In this work, we evaluate and compare five voxel similarity measures: Euclidean distance (ED), Log-Euclidean distance (LOG), distance based on diffusion profiles (DP), diffusion mode based similarity (MBS), and multichannel version of sum of squared differences (SSD). In evaluation we used an optimization-independent evaluation protocol to assess the capture range, the number of local minima, and cyclic registrations to evaluate consistency. Statistically significant differences were observed: DP and MBS were found to be the most consistent similarity measures, ED had the least number of local minima, and SSD was inferior to other similarity measures in all evaluations.",

keywords = "Image processing, Image registration",

author = "Mika Pollari and Tuomas Neuvonen and Mikko Lilja and Jyrki L{\"o}tj{\"o}nen",

year = "2007",

doi = "10.1109/ISBI.2007.356965",

language = "English",

isbn = "978-1-4244-0671-5",

pages = "768--771",

booktitle = "2007 4th IEEE International Symposium on Biomedical Imaging:",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

note = "4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2007 ; Conference date: 12-04-2007 Through 15-04-2007",

}

Pollari, M, Neuvonen, T, Lilja, M & Lötjönen, J 2007, Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images. in 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE Institute of Electrical and Electronic Engineers, pp. 768-771, 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2007, Arlington, VA, United States, 12/04/07. https://doi.org/10.1109/ISBI.2007.356965

Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images. / Pollari, Mika; Neuvonen, Tuomas; Lilja, Mikko et al.
2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE Institute of Electrical and Electronic Engineers, 2007. p. 768-771.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images

AU - Pollari, Mika

AU - Neuvonen, Tuomas

AU - Lilja, Mikko

AU - Lötjönen, Jyrki

PY - 2007

Y1 - 2007

N2 - Deriving an accurate cost function for tensor valued data has been one of the main difficulties in diffusion tensor image (DTI) registration. In this work, we evaluate and compare five voxel similarity measures: Euclidean distance (ED), Log-Euclidean distance (LOG), distance based on diffusion profiles (DP), diffusion mode based similarity (MBS), and multichannel version of sum of squared differences (SSD). In evaluation we used an optimization-independent evaluation protocol to assess the capture range, the number of local minima, and cyclic registrations to evaluate consistency. Statistically significant differences were observed: DP and MBS were found to be the most consistent similarity measures, ED had the least number of local minima, and SSD was inferior to other similarity measures in all evaluations.

AB - Deriving an accurate cost function for tensor valued data has been one of the main difficulties in diffusion tensor image (DTI) registration. In this work, we evaluate and compare five voxel similarity measures: Euclidean distance (ED), Log-Euclidean distance (LOG), distance based on diffusion profiles (DP), diffusion mode based similarity (MBS), and multichannel version of sum of squared differences (SSD). In evaluation we used an optimization-independent evaluation protocol to assess the capture range, the number of local minima, and cyclic registrations to evaluate consistency. Statistically significant differences were observed: DP and MBS were found to be the most consistent similarity measures, ED had the least number of local minima, and SSD was inferior to other similarity measures in all evaluations.

KW - Image processing

KW - Image registration

U2 - 10.1109/ISBI.2007.356965

DO - 10.1109/ISBI.2007.356965

M3 - Conference article in proceedings

SN - 978-1-4244-0671-5

SP - 768

EP - 771

BT - 2007 4th IEEE International Symposium on Biomedical Imaging:

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2007

Y2 - 12 April 2007 through 15 April 2007

ER -

Comparative evaluation of voxel similarity measures for affine registration of diffusion tensor MR images

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this