Ultrasound super-resolution imaging with a hierarchical Kalman tracker

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Standard

Ultrasound super-resolution imaging with a hierarchical Kalman tracker. / Taghavi, Iman; Andersen, Sofie Bech; Hoyos, Carlos Armando Villagómez; Schou, Mikkel; Gran, Fredrik; Hansen, Kristoffer Lindskov; Nielsen, Michael Bachmann; Sørensen, Charlotte Mehlin; Stuart, Matthias Bo; Jensen, Jørgen Arendt.

I: Ultrasonics, Bind 122, 106695, 2022.

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Harvard

Taghavi, I, Andersen, SB, Hoyos, CAV, Schou, M, Gran, F, Hansen, KL, Nielsen, MB, Sørensen, CM, Stuart, MB & Jensen, JA 2022, 'Ultrasound super-resolution imaging with a hierarchical Kalman tracker', Ultrasonics, bind 122, 106695. https://doi.org/10.1016/j.ultras.2022.106695

APA

Taghavi, I., Andersen, S. B., Hoyos, C. A. V., Schou, M., Gran, F., Hansen, K. L., Nielsen, M. B., Sørensen, C. M., Stuart, M. B., & Jensen, J. A. (2022). Ultrasound super-resolution imaging with a hierarchical Kalman tracker. Ultrasonics, 122, [106695]. https://doi.org/10.1016/j.ultras.2022.106695

Vancouver

Taghavi I, Andersen SB, Hoyos CAV, Schou M, Gran F, Hansen KL o.a. Ultrasound super-resolution imaging with a hierarchical Kalman tracker. Ultrasonics. 2022;122. 106695. https://doi.org/10.1016/j.ultras.2022.106695

Author

Taghavi, Iman ; Andersen, Sofie Bech ; Hoyos, Carlos Armando Villagómez ; Schou, Mikkel ; Gran, Fredrik ; Hansen, Kristoffer Lindskov ; Nielsen, Michael Bachmann ; Sørensen, Charlotte Mehlin ; Stuart, Matthias Bo ; Jensen, Jørgen Arendt. / Ultrasound super-resolution imaging with a hierarchical Kalman tracker. I: Ultrasonics. 2022 ; Bind 122.

Bibtex

@article{1171123e8f3348b589ae9860669f0936,
title = "Ultrasound super-resolution imaging with a hierarchical Kalman tracker",
abstract = "Microbubble (MB) tracking plays an important role in ultrasound super-resolution imaging (SRI) by enabling velocity estimation and improving image quality. This work presents a new hierarchical Kalman (HK) tracker to achieve better performance at scenarios with high concentrations of MBs and high localization uncertainty. The method attempts to follow MBs with different velocity ranges using different Kalman filters. An extended simulation framework for evaluating trackers is also presented and used for comparison of the proposed HK tracker with the nearest-neighbor (NN) and Kalman (K) trackers. The HK tracks were most similar to the ground truth with the highest Jaccard similarity coefficient in 79% of the scenarios and the lowest root-mean-square error in 72% of the scenarios. The HK tracker reconstructed vessels with a more accurate diameter. In a scenario with an uncertainty of 51.2μm in MB localization, a vessel diameter of 250μm was estimated as 257μm by HK tracker, compared with 329μm and 389μm for the K and NN trackers. In the same scenario, the HK tracker estimated MB velocities with a relative bias down to 1.7% and a relative standard deviation down to 8.3%. Finally, the different tracking techniques were applied to in vivo data from rat kidneys, and trends similar to the simulations were observed. Conclusively, the results showed an improvement in tracking performance, when the HK tracker was employed in comparison with the NN and K trackers.",
author = "Iman Taghavi and Andersen, {Sofie Bech} and Hoyos, {Carlos Armando Villag{\'o}mez} and Mikkel Schou and Fredrik Gran and Hansen, {Kristoffer Lindskov} and Nielsen, {Michael Bachmann} and S{\o}rensen, {Charlotte Mehlin} and Stuart, {Matthias Bo} and Jensen, {J{\o}rgen Arendt}",
note = "Copyright {\textcopyright} 2022 The Authors. Published by Elsevier B.V. All rights reserved.",
year = "2022",
doi = "10.1016/j.ultras.2022.106695",
language = "English",
volume = "122",
journal = "Ultrasonics",
issn = "0041-624X",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Ultrasound super-resolution imaging with a hierarchical Kalman tracker

AU - Taghavi, Iman

AU - Andersen, Sofie Bech

AU - Hoyos, Carlos Armando Villagómez

AU - Schou, Mikkel

AU - Gran, Fredrik

AU - Hansen, Kristoffer Lindskov

AU - Nielsen, Michael Bachmann

AU - Sørensen, Charlotte Mehlin

AU - Stuart, Matthias Bo

AU - Jensen, Jørgen Arendt

N1 - Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.

PY - 2022

Y1 - 2022

N2 - Microbubble (MB) tracking plays an important role in ultrasound super-resolution imaging (SRI) by enabling velocity estimation and improving image quality. This work presents a new hierarchical Kalman (HK) tracker to achieve better performance at scenarios with high concentrations of MBs and high localization uncertainty. The method attempts to follow MBs with different velocity ranges using different Kalman filters. An extended simulation framework for evaluating trackers is also presented and used for comparison of the proposed HK tracker with the nearest-neighbor (NN) and Kalman (K) trackers. The HK tracks were most similar to the ground truth with the highest Jaccard similarity coefficient in 79% of the scenarios and the lowest root-mean-square error in 72% of the scenarios. The HK tracker reconstructed vessels with a more accurate diameter. In a scenario with an uncertainty of 51.2μm in MB localization, a vessel diameter of 250μm was estimated as 257μm by HK tracker, compared with 329μm and 389μm for the K and NN trackers. In the same scenario, the HK tracker estimated MB velocities with a relative bias down to 1.7% and a relative standard deviation down to 8.3%. Finally, the different tracking techniques were applied to in vivo data from rat kidneys, and trends similar to the simulations were observed. Conclusively, the results showed an improvement in tracking performance, when the HK tracker was employed in comparison with the NN and K trackers.

AB - Microbubble (MB) tracking plays an important role in ultrasound super-resolution imaging (SRI) by enabling velocity estimation and improving image quality. This work presents a new hierarchical Kalman (HK) tracker to achieve better performance at scenarios with high concentrations of MBs and high localization uncertainty. The method attempts to follow MBs with different velocity ranges using different Kalman filters. An extended simulation framework for evaluating trackers is also presented and used for comparison of the proposed HK tracker with the nearest-neighbor (NN) and Kalman (K) trackers. The HK tracks were most similar to the ground truth with the highest Jaccard similarity coefficient in 79% of the scenarios and the lowest root-mean-square error in 72% of the scenarios. The HK tracker reconstructed vessels with a more accurate diameter. In a scenario with an uncertainty of 51.2μm in MB localization, a vessel diameter of 250μm was estimated as 257μm by HK tracker, compared with 329μm and 389μm for the K and NN trackers. In the same scenario, the HK tracker estimated MB velocities with a relative bias down to 1.7% and a relative standard deviation down to 8.3%. Finally, the different tracking techniques were applied to in vivo data from rat kidneys, and trends similar to the simulations were observed. Conclusively, the results showed an improvement in tracking performance, when the HK tracker was employed in comparison with the NN and K trackers.

U2 - 10.1016/j.ultras.2022.106695

DO - 10.1016/j.ultras.2022.106695

M3 - Journal article

C2 - 35149256

VL - 122

JO - Ultrasonics

JF - Ultrasonics

SN - 0041-624X

M1 - 106695

ER -

ID: 291982016