ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions

Nora Ouzir; Esa Ollila; Sergiy A. Vorobyov

doi:10.1109/CAMSAP45676.2019.9022664

ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions

Nora Ouzir, Esa Ollila, Sergiy A. Vorobyov

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

The multiplicative Rayleigh noise model has been used for maximum likelihood (ML) motion estimation in ultrasound imaging (UI). In this work, we introduce new robust similarity measures that take into account the deviations from the Rayleigh statistics resulting, for example, from multiple scatterings or acquisition artefacts. Specifically, the t-distribution is used for modelling the radio-frequency (RF) signals and the Nakagami-Gamma (NG) model is used for the echo amplitudes. Experiments using in vivo images of the carotid artery show an improvement in motion estimation accuracy in comparison with the similarity measure based on the classical Rayleigh model.

Original language	English
Title of host publication	2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings
Publisher	IEEE
Pages	366-370
Number of pages	5
ISBN (Electronic)	9781728155494
DOIs	https://doi.org/10.1109/CAMSAP45676.2019.9022664
Publication status	Published - 1 Dec 2019
MoE publication type	A4 Article in a conference publication
Event	IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing - Guadeloupe, Le Gosier, Guadeloupe Duration: 15 Dec 2019 → 18 Dec 2019 Conference number: 18 https://camsap19.ig.umons.ac.be

Workshop

Workshop	IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing
Abbreviated title	CAMSAP
Country/Territory	Guadeloupe
City	Le Gosier
Period	15/12/2019 → 18/12/2019
Internet address	https://camsap19.ig.umons.ac.be

Access to Document

10.1109/CAMSAP45676.2019.9022664

OpenUrl availability

Full text

Cite this

@inproceedings{6a613a4442dc4b0b926857814b8f6ba8,

title = "ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions",

abstract = "The multiplicative Rayleigh noise model has been used for maximum likelihood (ML) motion estimation in ultrasound imaging (UI). In this work, we introduce new robust similarity measures that take into account the deviations from the Rayleigh statistics resulting, for example, from multiple scatterings or acquisition artefacts. Specifically, the t-distribution is used for modelling the radio-frequency (RF) signals and the Nakagami-Gamma (NG) model is used for the echo amplitudes. Experiments using in vivo images of the carotid artery show an improvement in motion estimation accuracy in comparison with the similarity measure based on the classical Rayleigh model.",

author = "Nora Ouzir and Esa Ollila and Vorobyov, {Sergiy A.}",

year = "2019",

month = dec,

day = "1",

doi = "10.1109/CAMSAP45676.2019.9022664",

language = "English",

pages = "366--370",

booktitle = "2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP ; Conference date: 15-12-2019 Through 18-12-2019",

url = "https://camsap19.ig.umons.ac.be",

}

Ouzir, N, Ollila, E & Vorobyov, SA 2019, ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions. in 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings., 9022664, IEEE, pp. 366-370, IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, Le Gosier, Guadeloupe, 15/12/2019. https://doi.org/10.1109/CAMSAP45676.2019.9022664

ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions. / Ouzir, Nora; Ollila, Esa ; Vorobyov, Sergiy A.

2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings. IEEE, 2019. p. 366-370 9022664.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions

AU - Ouzir, Nora

AU - Ollila, Esa

AU - Vorobyov, Sergiy A.

N1 - Conference code: 18

PY - 2019/12/1

Y1 - 2019/12/1

N2 - The multiplicative Rayleigh noise model has been used for maximum likelihood (ML) motion estimation in ultrasound imaging (UI). In this work, we introduce new robust similarity measures that take into account the deviations from the Rayleigh statistics resulting, for example, from multiple scatterings or acquisition artefacts. Specifically, the t-distribution is used for modelling the radio-frequency (RF) signals and the Nakagami-Gamma (NG) model is used for the echo amplitudes. Experiments using in vivo images of the carotid artery show an improvement in motion estimation accuracy in comparison with the similarity measure based on the classical Rayleigh model.

AB - The multiplicative Rayleigh noise model has been used for maximum likelihood (ML) motion estimation in ultrasound imaging (UI). In this work, we introduce new robust similarity measures that take into account the deviations from the Rayleigh statistics resulting, for example, from multiple scatterings or acquisition artefacts. Specifically, the t-distribution is used for modelling the radio-frequency (RF) signals and the Nakagami-Gamma (NG) model is used for the echo amplitudes. Experiments using in vivo images of the carotid artery show an improvement in motion estimation accuracy in comparison with the similarity measure based on the classical Rayleigh model.

UR - http://www.scopus.com/inward/record.url?scp=85082390844&partnerID=8YFLogxK

U2 - 10.1109/CAMSAP45676.2019.9022664

DO - 10.1109/CAMSAP45676.2019.9022664

M3 - Conference contribution

SP - 366

EP - 370

BT - 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2019 - Proceedings

PB - IEEE

T2 - IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing

Y2 - 15 December 2019 through 18 December 2019

ER -

ML-based Motion Estimation in Ultrasound Images Using Heavy-tailed Noise Distributions

Abstract

Workshop

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this