A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images

Akshay Sadananda Uppinakudru Pai; Stefan Horst Sommer; Lars Lau Raket; Line Kühnel; Sune Darkner; Lauge Sørensen; Mads Nielsen

doi:10.1007/978-3-319-61188-4_14

A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images

Akshay Sadananda Uppinakudru Pai, Stefan Horst Sommer, Lars Lau Raket, Line Kühnel, Sune Darkner, Lauge Sørensen, Mads Nielsen

Department of Computer Science

Abstract

Template estimation plays a crucial role in computational anatomy since it provides reference frames for performing statistical analysis of the underlying anatomical population variability. While building models for template estimation, variability in sites and image acquisition protocols need to be accounted for. To account for such variability, we propose a generative template estimation model that makes simultaneous inference of both bias fields in individual images, deformations for image registration, and variance hyperparameters. In contrast, existing maximum a posterori based methods need to rely on either bias-invariant similarity measures or robust image normalization. Results on synthetic and real brain MRI images demonstrate the capability of the model to capture heterogeneity in intensities and provide a reliable template estimation from registration.

Original language	English
Title of host publication	Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging : MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers
Editors	Henning Müller, B. Michael Kelm, Tal Arbel, Weidong Cai, M. Jorge Cardoso, Georg Langs, Bjoern Menze, Dmitris Metaxas, Albert Montillo, William M. Wells, Shaoting Zhang, Albert C. S. Chung, Mark Jenkinson, Annemie Ribbens
Number of pages	9
Publisher	Springer
Publication date	2017
Pages	151-159
ISBN (Print)	978-3-319-61187-7
ISBN (Electronic)	978-3-319-61188-4
DOIs	https://doi.org/10.1007/978-3-319-61188-4_14
Publication status	Published - 2017
Event	3rd International Workshop on Bayesian and Graphical Models for Biomedical Imaging - Athen, Greece Duration: 21 Oct 2016 → 21 Oct 2016 Conference number: 3

Workshop

Workshop	3rd International Workshop on Bayesian and Graphical Models for Biomedical Imaging
Number	3
Country/Territory	Greece
City	Athen
Period	21/10/2016 → 21/10/2016

Series	Lecture notes in computer science
Volume	10081
ISSN	0302-9743

Access to Document

10.1007/978-3-319-61188-4_14

https://arxiv.org/pdf/1705.00432.pdf

Cite this

Pai, A. S. U., Sommer, S. H., Raket, L. L., Kühnel, L., Darkner, S., Sørensen, L., & Nielsen, M. (2017). A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images. In H. Müller, B. M. Kelm, T. Arbel, W. Cai, M. J. Cardoso, G. Langs, B. Menze, D. Metaxas, A. Montillo, W. M. Wells, S. Zhang, A. C. S. Chung, M. Jenkinson, & A. Ribbens (Eds.), Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging: MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers (pp. 151-159). Springer. https://doi.org/10.1007/978-3-319-61188-4_14

A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images. / Pai, Akshay Sadananda Uppinakudru ; Sommer, Stefan Horst; Raket, Lars Lau et al.
Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging: MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers. ed. / Henning Müller; B. Michael Kelm; Tal Arbel; Weidong Cai; M. Jorge Cardoso; Georg Langs; Bjoern Menze; Dmitris Metaxas; Albert Montillo; William M. Wells; Shaoting Zhang; Albert C. S. Chung; Mark Jenkinson; Annemie Ribbens. Springer, 2017. p. 151-159 (Lecture notes in computer science, Vol. 10081).

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

Pai, ASU , Sommer, SH, Raket, LL, Kühnel, L, Darkner, S , Sørensen, L & Nielsen, M 2017, A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images. in H Müller, BM Kelm, T Arbel, W Cai, MJ Cardoso, G Langs, B Menze, D Metaxas, A Montillo, WM Wells, S Zhang, ACS Chung, M Jenkinson & A Ribbens (eds), Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging: MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers. Springer, Lecture notes in computer science, vol. 10081, pp. 151-159, 3rd International Workshop on Bayesian and Graphical Models for Biomedical Imaging, Athen, Greece, 21/10/2016. https://doi.org/10.1007/978-3-319-61188-4_14

Pai ASU , Sommer SH, Raket LL, Kühnel L, Darkner S , Sørensen L et al. A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images. In Müller H, Kelm BM, Arbel T, Cai W, Cardoso MJ, Langs G, Menze B, Metaxas D, Montillo A, Wells WM, Zhang S, Chung ACS, Jenkinson M, Ribbens A, editors, Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging: MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers. Springer. 2017. p. 151-159. (Lecture notes in computer science, Vol. 10081). doi: 10.1007/978-3-319-61188-4_14

Pai, Akshay Sadananda Uppinakudru ; Sommer, Stefan Horst ; Raket, Lars Lau et al. / A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images. Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging: MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers. editor / Henning Müller ; B. Michael Kelm ; Tal Arbel ; Weidong Cai ; M. Jorge Cardoso ; Georg Langs ; Bjoern Menze ; Dmitris Metaxas ; Albert Montillo ; William M. Wells ; Shaoting Zhang ; Albert C. S. Chung ; Mark Jenkinson ; Annemie Ribbens. Springer, 2017. pp. 151-159 (Lecture notes in computer science, Vol. 10081).

@inproceedings{24208255fe364acaa7c0a1b4af91461e,

title = "A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images",

abstract = "Template estimation plays a crucial role in computational anatomy since it provides reference frames for performing statistical analysis of the underlying anatomical population variability. While building models for template estimation, variability in sites and image acquisition protocols need to be accounted for. To account for such variability, we propose a generative template estimation model that makes simultaneous inference of both bias fields in individual images, deformations for image registration, and variance hyperparameters. In contrast, existing maximum a posterori based methods need to rely on either bias-invariant similarity measures or robust image normalization. Results on synthetic and real brain MRI images demonstrate the capability of the model to capture heterogeneity in intensities and provide a reliable template estimation from registration.",

author = "Pai, {Akshay Sadananda Uppinakudru} and Sommer, {Stefan Horst} and Raket, {Lars Lau} and Line K{\"u}hnel and Sune Darkner and Lauge S{\o}rensen and Mads Nielsen",

year = "2017",

doi = "10.1007/978-3-319-61188-4_14",

language = "English",

isbn = "978-3-319-61187-7",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "151--159",

editor = "Henning M{\"u}ller and Kelm, {B. Michael} and Tal Arbel and Weidong Cai and Cardoso, {M. Jorge} and Georg Langs and Bjoern Menze and Dmitris Metaxas and Albert Montillo and Wells, {William M.} and Shaoting Zhang and Chung, {Albert C. S.} and Mark Jenkinson and Annemie Ribbens",

booktitle = "Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging",

note = "3rd International Workshop on Bayesian and Graphical Models for Biomedical Imaging ; Conference date: 21-10-2016 Through 21-10-2016",

}

TY - GEN

T1 - A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images

AU - Pai, Akshay Sadananda Uppinakudru

AU - Sommer, Stefan Horst

AU - Raket, Lars Lau

AU - Kühnel, Line

AU - Darkner, Sune

AU - Sørensen, Lauge

AU - Nielsen, Mads

N1 - Conference code: 3

PY - 2017

Y1 - 2017

N2 - Template estimation plays a crucial role in computational anatomy since it provides reference frames for performing statistical analysis of the underlying anatomical population variability. While building models for template estimation, variability in sites and image acquisition protocols need to be accounted for. To account for such variability, we propose a generative template estimation model that makes simultaneous inference of both bias fields in individual images, deformations for image registration, and variance hyperparameters. In contrast, existing maximum a posterori based methods need to rely on either bias-invariant similarity measures or robust image normalization. Results on synthetic and real brain MRI images demonstrate the capability of the model to capture heterogeneity in intensities and provide a reliable template estimation from registration.

AB - Template estimation plays a crucial role in computational anatomy since it provides reference frames for performing statistical analysis of the underlying anatomical population variability. While building models for template estimation, variability in sites and image acquisition protocols need to be accounted for. To account for such variability, we propose a generative template estimation model that makes simultaneous inference of both bias fields in individual images, deformations for image registration, and variance hyperparameters. In contrast, existing maximum a posterori based methods need to rely on either bias-invariant similarity measures or robust image normalization. Results on synthetic and real brain MRI images demonstrate the capability of the model to capture heterogeneity in intensities and provide a reliable template estimation from registration.

U2 - 10.1007/978-3-319-61188-4_14

DO - 10.1007/978-3-319-61188-4_14

M3 - Article in proceedings

SN - 978-3-319-61187-7

T3 - Lecture notes in computer science

SP - 151

EP - 159

BT - Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging

A2 - Müller, Henning

A2 - Kelm, B. Michael

A2 - Arbel, Tal

A2 - Cai, Weidong

A2 - Cardoso, M. Jorge

A2 - Langs, Georg

A2 - Menze, Bjoern

A2 - Metaxas, Dmitris

A2 - Montillo, Albert

A2 - Wells, William M.

A2 - Zhang, Shaoting

A2 - Chung, Albert C. S.

A2 - Jenkinson, Mark

A2 - Ribbens, Annemie

PB - Springer

T2 - 3rd International Workshop on Bayesian and Graphical Models for Biomedical Imaging

Y2 - 21 October 2016 through 21 October 2016

ER -

A statistical model for simultaneous template estimation, bias correction, and registration of 3D brain images

Abstract

Workshop

Access to Document

Fingerprint

Cite this