Image registration using stationary velocity fields parameterized by norm-minimizing Wendland kernel

Akshay Sadananda Uppinakudru Pai; Stefan Horst Sommer; Lauge Sørensen; Sune Darkner; Jon Sporring; Mads Nielsen

doi:10.1117/12.2076469

Image registration using stationary velocity fields parameterized by norm-minimizing Wendland kernel

Akshay Sadananda Uppinakudru Pai, Stefan Horst Sommer, Lauge Sørensen, Sune Darkner, Jon Sporring, Mads Nielsen

Department of Computer Science

4 Citations (Scopus)

Abstract

Interpolating kernels are crucial to solving a stationary velocity field (SVF) based image registration problem. This is because, velocity fields need to be computed in non-integer locations during integration. The regularity in the solution to the SVF registration problem is controlled by the regularization term. In a variational formulation, this term is traditionally expressed as a squared norm which is a scalar inner product of the interpolating kernels parameterizing the velocity fields. The minimization of this term using the standard spline interpolation kernels (linear or cubic) is only approximative because of the lack of a compatible norm. In this paper, we propose to replace such interpolants with a norm-minimizing interpolant-the Wendland kernel which has the same computational simplicity like B-Splines. An application on the Alzheimer's disease neuroimaging initiative showed that Wendland SVF based measures separate (Alzheimer's disease v/s normal controls) better than both B-Spline SVFs (p<0.05 in amygdala) and B-Spline freeform deformation (p<0.05 in amygdala and cortical gray matter).

Original language	Danish
Publication date	2015
Number of pages	1
DOIs	https://doi.org/10.1117/12.2076469
Publication status	Published - 2015
Event	SPIE Medical Imaging 2015 - , Denmark Duration: 14 May 2015 → …

Conference

Conference	SPIE Medical Imaging 2015
Country/Territory	Denmark
Period	14/05/2015 → …

Access to Document

10.1117/12.2076469

Cite this

@conference{f8a19705b6864cad90dbaba7f0ab3ecd,

title = "Image registration using stationary velocity fields parameterized by norm-minimizing Wendland kernel",

abstract = " Interpolating kernels are crucial to solving a stationary velocity field (SVF) based image registration problem. This is because, velocity fields need to be computed in non-integer locations during integration. The regularity in the solution to the SVF registration problem is controlled by the regularization term. In a variational formulation, this term is traditionally expressed as a squared norm which is a scalar inner product of the interpolating kernels parameterizing the velocity fields. The minimization of this term using the standard spline interpolation kernels (linear or cubic) is only approximative because of the lack of a compatible norm. In this paper, we propose to replace such interpolants with a norm-minimizing interpolant - the Wendland kernel which has the same computational simplicity like B-Splines. An application on the Alzheimer's disease neuroimaging initiative showed that Wendland SVF based measures separate (Alzheimer's disease v/s normal controls) better than both B-Spline SVFs (p<0.05 in amygdala) and B-Spline freeform deformation (p<0.05 in amygdala and cortical gray matter).",

author = "Pai, {Akshay Sadananda Uppinakudru} and Sommer, {Stefan Horst} and Lauge S{\o}rensen and Sune Darkner and Jon Sporring and Mads Nielsen",

year = "2015",

doi = "10.1117/12.2076469",

language = "Dansk",

note = "SPIE Medical Imaging 2015 ; Conference date: 14-05-2015",

}

TY - CONF

T1 - Image registration using stationary velocity fields parameterized by norm-minimizing Wendland kernel

AU - Pai, Akshay Sadananda Uppinakudru

AU - Sommer, Stefan Horst

AU - Sørensen, Lauge

AU - Darkner, Sune

AU - Sporring, Jon

AU - Nielsen, Mads

PY - 2015

Y1 - 2015

N2 - Interpolating kernels are crucial to solving a stationary velocity field (SVF) based image registration problem. This is because, velocity fields need to be computed in non-integer locations during integration. The regularity in the solution to the SVF registration problem is controlled by the regularization term. In a variational formulation, this term is traditionally expressed as a squared norm which is a scalar inner product of the interpolating kernels parameterizing the velocity fields. The minimization of this term using the standard spline interpolation kernels (linear or cubic) is only approximative because of the lack of a compatible norm. In this paper, we propose to replace such interpolants with a norm-minimizing interpolant - the Wendland kernel which has the same computational simplicity like B-Splines. An application on the Alzheimer's disease neuroimaging initiative showed that Wendland SVF based measures separate (Alzheimer's disease v/s normal controls) better than both B-Spline SVFs (p<0.05 in amygdala) and B-Spline freeform deformation (p<0.05 in amygdala and cortical gray matter).

AB - Interpolating kernels are crucial to solving a stationary velocity field (SVF) based image registration problem. This is because, velocity fields need to be computed in non-integer locations during integration. The regularity in the solution to the SVF registration problem is controlled by the regularization term. In a variational formulation, this term is traditionally expressed as a squared norm which is a scalar inner product of the interpolating kernels parameterizing the velocity fields. The minimization of this term using the standard spline interpolation kernels (linear or cubic) is only approximative because of the lack of a compatible norm. In this paper, we propose to replace such interpolants with a norm-minimizing interpolant - the Wendland kernel which has the same computational simplicity like B-Splines. An application on the Alzheimer's disease neuroimaging initiative showed that Wendland SVF based measures separate (Alzheimer's disease v/s normal controls) better than both B-Spline SVFs (p<0.05 in amygdala) and B-Spline freeform deformation (p<0.05 in amygdala and cortical gray matter).

U2 - 10.1117/12.2076469

DO - 10.1117/12.2076469

M3 - Poster

T2 - SPIE Medical Imaging 2015

Y2 - 14 May 2015

ER -