Fast reconstruction of image deformation field using radial
basis function

D 2017

Fast reconstruction of image deformation field using radial basis function

RUČKA, Lukáš and Igor PETERLÍK

Basic information

Original name

Fast reconstruction of image deformation field using radial basis function

Authors

RUČKA, Lukáš (203 Czech Republic, belonging to the institution) and Igor PETERLÍK (703 Slovakia, guarantor, belonging to the institution)

Edition

Neuveden, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI), p. 1146-1150, 5 pp. 2017

Publisher

IEEE

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14330/17:00097217

Organization unit

Faculty of Informatics

ISBN

978-1-5090-1171-1

ISSN

DOI

http://dx.doi.org/10.1109/ISBI.2017.7950719

UT WoS

000414283200265

Keywords in English

image warping; image interpolation; medical imaging; non-rigid registration

Abstract

V originále

Fast and accurate registration of image data is a key component of computer-aided medical image analysis. Instead of performing the registration directly on the input images, many algorithms compute the transformation using a sparse representation extracted from the original data. However, in order to apply the resulting transformation onto the original images, a dense deformation field has to be reconstructed using a suitable inter-/extra-polation technique. In this paper, we employ the radial basis function (RBF) to reconstruct the dense deformation field from a sparse transformation computed by a model-based registration. Various kernels are tested using different scenario. The dense deformation field is used to warp the source image and compare it quantitatively to the target image using two different metrics. Moreover, the influence of the number and distribution of the control points required by the RBF is studied via two different scenarios. Beside the accuracy, the performance of the method accelerated using a GPU is reported.

Links

MUNI/A/0897/2016, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VI.

Investor: Masaryk University, Category A

Citovat

RUČKA, Lukáš and Igor PETERLÍK. Fast reconstruction of image deformation field using radial basis function. Online. In 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI). Neuveden: IEEE, 2017, p. 1146-1150. ISBN 978-1-5090-1171-1. Available from: https://dx.doi.org/10.1109/ISBI.2017.7950719.

@inproceedings{1386003,
   author = {Ručka, Lukáš and Peterlík, Igor},
   address = {Neuveden},
   booktitle = {2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI)},
   doi = {http://dx.doi.org/10.1109/ISBI.2017.7950719},
   keywords = {image warping; image interpolation; medical imaging; non-rigid registration},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   isbn = {978-1-5090-1171-1},
   pages = {1146-1150},
   publisher = {IEEE},
   title = {Fast reconstruction of image deformation field using radial basis function},
   url = {http://ieeexplore.ieee.org/document/7950719/},
   year = {2017}
}

TY  - JOUR
ID  - 1386003
AU  - Ručka, Lukáš - Peterlík, Igor
PY  - 2017
TI  - Fast reconstruction of image deformation field using radial basis function
PB  - IEEE
CY  - Neuveden
SN  - 9781509011711
KW  - image warping
KW  - image interpolation
KW  - medical imaging
KW  - non-rigid registration
UR  - http://ieeexplore.ieee.org/document/7950719/
L2  - http://ieeexplore.ieee.org/document/7950719/
N2  - Fast and accurate registration of image data is a key component of computer-aided medical image analysis. Instead of performing the registration directly on the input images, many algorithms compute the transformation using a sparse representation extracted from the original data. However, in order to apply the resulting transformation onto the original images, a dense deformation field has to be reconstructed using a suitable inter-/extra-polation technique. In this paper, we employ the radial basis function (RBF) to reconstruct the dense deformation field from a sparse transformation computed by a model-based registration. Various kernels are tested using different scenario. The dense deformation field is used to warp the source image and compare it quantitatively to the target image using two different metrics. Moreover, the influence of the number and distribution of the control points required by the RBF is studied via two different scenarios. Beside the accuracy, the performance of the method accelerated using a GPU is reported.
ER  -

RUČKA, Lukáš and Igor PETERLÍK. Fast reconstruction of image deformation field using radial basis function. Online. In \textit{2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI)}. Neuveden: IEEE, 2017, p.~1146-1150. ISBN~978-1-5090-1171-1. Available from: https://dx.doi.org/10.1109/ISBI.2017.7950719.

Detailed Information on Publication Record