A Regression Model for Registering Multimodal Images

Thomas Deregnaucourt; Chafik Samir; Anne Francoise Yao

doi:10.1016/j.procs.2016.07.008

A Regression Model for Registering Multimodal Images

Thomas Deregnaucourt
, Chafik Samir
, Anne Francoise Yao

Clermont-Auvergne University

Research output: Contribution to journal › Conference article › peer-review

Abstract

We propose a new multimodal image registration method when using different imaging modalities separately. The proposed method first aligns corresponding extracted geometric features (continuous curves), and then estimate the deformation vector field as spatial stochastic processes. The resulting deformation has the advantage of registering the given data in such a way that the corresponding curves-regions match as being sufficiently smooth over the whole image domain. Experimental results on both synthetic and real data show that the proposed method matches the state-of-the-art.

Original language	English
Pages (from-to)	42-47
Number of pages	6
Journal	Procedia Computer Science
Volume	90
DOIs	https://doi.org/10.1016/j.procs.2016.07.008
Publication status	Published - 1 Jan 2016
Externally published	Yes
Event	20th Conference on Medical Image Understanding and Analysis, MIUA 2016 - , United Kingdom Duration: 6 Jul 2016 → 8 Jul 2016

Keywords

Elastic registration
Gaussian random field
Manifold embedding
Multimodal registration
Regression
Smooth deformation vector field
Stochastic process

Access to Document

10.1016/j.procs.2016.07.008

Cite this

@article{f481f486281a423c85ad1ab63be918dd,

title = "A Regression Model for Registering Multimodal Images",

abstract = "We propose a new multimodal image registration method when using different imaging modalities separately. The proposed method first aligns corresponding extracted geometric features (continuous curves), and then estimate the deformation vector field as spatial stochastic processes. The resulting deformation has the advantage of registering the given data in such a way that the corresponding curves-regions match as being sufficiently smooth over the whole image domain. Experimental results on both synthetic and real data show that the proposed method matches the state-of-the-art.",

keywords = "Elastic registration, Gaussian random field, Manifold embedding, Multimodal registration, Regression, Smooth deformation vector field, Stochastic process",

author = "Thomas Deregnaucourt and Chafik Samir and Yao, \{Anne Francoise\}",

note = "Publisher Copyright: {\textcopyright} 2016 The Authors. Published by Elsevier B.V.; 20th Conference on Medical Image Understanding and Analysis, MIUA 2016 ; Conference date: 06-07-2016 Through 08-07-2016",

year = "2016",

month = jan,

day = "1",

doi = "10.1016/j.procs.2016.07.008",

language = "English",

volume = "90",

pages = "42--47",

journal = "Procedia Computer Science",

issn = "1877-0509",

}

TY - JOUR

T1 - A Regression Model for Registering Multimodal Images

AU - Deregnaucourt, Thomas

AU - Samir, Chafik

AU - Yao, Anne Francoise

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We propose a new multimodal image registration method when using different imaging modalities separately. The proposed method first aligns corresponding extracted geometric features (continuous curves), and then estimate the deformation vector field as spatial stochastic processes. The resulting deformation has the advantage of registering the given data in such a way that the corresponding curves-regions match as being sufficiently smooth over the whole image domain. Experimental results on both synthetic and real data show that the proposed method matches the state-of-the-art.

AB - We propose a new multimodal image registration method when using different imaging modalities separately. The proposed method first aligns corresponding extracted geometric features (continuous curves), and then estimate the deformation vector field as spatial stochastic processes. The resulting deformation has the advantage of registering the given data in such a way that the corresponding curves-regions match as being sufficiently smooth over the whole image domain. Experimental results on both synthetic and real data show that the proposed method matches the state-of-the-art.

KW - Elastic registration

KW - Gaussian random field

KW - Manifold embedding

KW - Multimodal registration

KW - Regression

KW - Smooth deformation vector field

KW - Stochastic process

UR - https://www.scopus.com/pages/publications/84985016847

U2 - 10.1016/j.procs.2016.07.008

DO - 10.1016/j.procs.2016.07.008

M3 - Conference article

AN - SCOPUS:84985016847

SN - 1877-0509

VL - 90

SP - 42

EP - 47

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 20th Conference on Medical Image Understanding and Analysis, MIUA 2016

Y2 - 6 July 2016 through 8 July 2016

ER -

A Regression Model for Registering Multimodal Images

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this