Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound

Shaun Bundervoet; Colas Schretter; Ann Dooms; Peter Schelkens

Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound

Shaun Bundervoet, Colas Schretter, Ann Dooms, Peter Schelkens

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

Abstract

Emerging ultrasound phased-array technologies will soon enable the acquisition of high-resolution 3D+T images for medical applications. Processing the huge amount of spatiotemporal measurements remains a practical challenge. In this work, dynamic ultrasound images are sparsely represented by a mixture of moving speckles. We model the shape of a speckle and its locally linear motion with a weighted multivariate Gaussian kernel. Parameters of the model are estimated with online Bayesian learning from a stream of random measurements. In our preliminary experiments with a simulated phantom of a moving cylindrical structure, the optical flow of speckles is estimated for a vertical line profile and compared to the ground truth. The mean accuracy of the linear motion estimate is of 93.53%, using only a statistically sufficient random subset of the data.

Original language	English
Title of host publication	iTWIST'14, international - Traveling Workshop on Interactions between Sparse models and Technology
Editors	Laurent Jacques
Number of pages	3
Publication status	Published - 2014
Event	iTWIST'14 international Traveling Workshop on Interactions between Sparse models and Technology - Namur, Belgium Duration: 27 Aug 2014 → 29 Aug 2014

Conference

Conference	iTWIST'14 international Traveling Workshop on Interactions between Sparse models and Technology
Country/Territory	Belgium
City	Namur
Period	27/08/14 → 29/08/14

Bibliographical note

Laurent Jacques

Keywords

Ultrasound imaging
Sparse image model

Access to Document

http://arxiv.org/abs/1410.0719

Handle.net

Persistent link

SRP11: Strategic Research Programme: Processing of large scale multi-dimensional, multi-spectral, multi-sensorial and distributed data (M³D²)
Schelkens, P. (Administrative Promotor), Deligiannis, N. (Co-Promotor), Jansen, B. (Co-Promotor), Kuijk, M. (Co-Promotor), Munteanu, A. (Co-Promotor), Sahli, H. (Co-Promotor), Steenhaut, K. (Co-Promotor), Stiens, J. (Co-Promotor), Schelkens, P. (Administrative Promotor), Cornelis, J. P. (Co-Promotor), Kuijk, M. (Co-Promotor), Munteanu, A. (Co-Promotor), Sahli, H. (Co-Promotor), Stiens, J. (Co-Promotor) & Vounckx, R. (Co-Promotor)
1/11/12 → 31/12/23
Project: Fundamental

Cite this

@inproceedings{28896d49a7ce467db556dc9b80d97468,

title = "Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound",

abstract = "Emerging ultrasound phased-array technologies will soon enable the acquisition of high-resolution 3D+T images for medical applications. Processing the huge amount of spatiotemporal measurements remains a practical challenge. In this work, dynamic ultrasound images are sparsely represented by a mixture of moving speckles. We model the shape of a speckle and its locally linear motion with a weighted multivariate Gaussian kernel. Parameters of the model are estimated with online Bayesian learning from a stream of random measurements. In our preliminary experiments with a simulated phantom of a moving cylindrical structure, the optical flow of speckles is estimated for a vertical line profile and compared to the ground truth. The mean accuracy of the linear motion estimate is of 93.53%, using only a statistically sufficient random subset of the data.",

keywords = "Ultrasound imaging, Sparse image model",

author = "Shaun Bundervoet and Colas Schretter and Ann Dooms and Peter Schelkens",

note = "Laurent Jacques; iTWIST'14 international Traveling Workshop on Interactions between Sparse models and Technology ; Conference date: 27-08-2014 Through 29-08-2014",

year = "2014",

language = "English",

editor = "Laurent Jacques",

booktitle = "iTWIST'14, international - Traveling Workshop on Interactions between Sparse models and Technology",

}

Bundervoet, S, Schretter, C , Dooms, A & Schelkens, P 2014, Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound. in L Jacques (ed.), iTWIST'14, international - Traveling Workshop on Interactions between Sparse models and Technology. iTWIST'14 international Traveling Workshop on Interactions between Sparse models and Technology, Namur, Belgium, 27/08/14. <http://arxiv.org/abs/1410.0719>

TY - GEN

T1 - Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound

AU - Bundervoet, Shaun

AU - Schretter, Colas

AU - Dooms, Ann

AU - Schelkens, Peter

N1 - Laurent Jacques

PY - 2014

Y1 - 2014

N2 - Emerging ultrasound phased-array technologies will soon enable the acquisition of high-resolution 3D+T images for medical applications. Processing the huge amount of spatiotemporal measurements remains a practical challenge. In this work, dynamic ultrasound images are sparsely represented by a mixture of moving speckles. We model the shape of a speckle and its locally linear motion with a weighted multivariate Gaussian kernel. Parameters of the model are estimated with online Bayesian learning from a stream of random measurements. In our preliminary experiments with a simulated phantom of a moving cylindrical structure, the optical flow of speckles is estimated for a vertical line profile and compared to the ground truth. The mean accuracy of the linear motion estimate is of 93.53%, using only a statistically sufficient random subset of the data.

AB - Emerging ultrasound phased-array technologies will soon enable the acquisition of high-resolution 3D+T images for medical applications. Processing the huge amount of spatiotemporal measurements remains a practical challenge. In this work, dynamic ultrasound images are sparsely represented by a mixture of moving speckles. We model the shape of a speckle and its locally linear motion with a weighted multivariate Gaussian kernel. Parameters of the model are estimated with online Bayesian learning from a stream of random measurements. In our preliminary experiments with a simulated phantom of a moving cylindrical structure, the optical flow of speckles is estimated for a vertical line profile and compared to the ground truth. The mean accuracy of the linear motion estimate is of 93.53%, using only a statistically sufficient random subset of the data.

KW - Ultrasound imaging

KW - Sparse image model

M3 - Conference paper

BT - iTWIST'14, international - Traveling Workshop on Interactions between Sparse models and Technology

A2 - Jacques, Laurent

T2 - iTWIST'14 international Traveling Workshop on Interactions between Sparse models and Technology

Y2 - 27 August 2014 through 29 August 2014

ER -

Bayesian Estimation of Sparse Smooth Speckle Shape Models for Motion Tracking in Medical Ultrasound

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Projects

SRP11: Strategic Research Programme: Processing of large scale multi-dimensional, multi-spectral, multi-sensorial and distributed data (M³D²)

Cite this