Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound

Deepak Roy Chittajallu, Matthew McCormick, Samuel Gerber, Tomasz J. Czernuszewicz, Ryan Gessner, Monte Willis, Marc Niethammer, Roland Kwitt, Stephen R. Aylward

Research output: Contribution to journalArticle

Abstract

Objective: Ultrasound is an effective tool for rapid noninvasive assessment of cardiac structure and function. Determining the cardiorespiratory phases of each frame in the ultrasound video and capturing the cardiac function at a much higher temporal resolution are essential in many applications. Fulfilling these requirements is particularly challenging in preclinical studies involving small animals with high cardiorespiratory rates, requiring cumbersome and expensive specialized hardware. Methods: We present a novel method for the retrospective estimation of cardiorespiratory phases directly from the ultrasound videos. It transforms the videos into a univariate time series preserving the evidence of periodic cardiorespiratory motion, decouples the signatures of cardiorespiratory motion with a trend extraction technique, and estimates the cardiorespiratory phases using a Hilbert transform approach. We also present a robust nonparametric regression technique for respiratory gating and a novel kernel-regression model for reconstructing images at any cardiac phase facilitating temporal superresolution. Results: We validated our methods using two-dimensional echocardiography videos and electrocardiogram (ECG) recordings of six mice. Our cardiac phase estimation method provides accurate phase estimates with a mean-phase-error range of 3%-6% against ECG derived phase and outperforms three previously published methods in locating ECGs R-wave peak frames with a mean-frame-error range of 0.73-1.36. Our kernel-regression model accurately reconstructs images at any cardiac phase with a mean-normalized-correlation range of 0.81-0.85 over 50 leave-one-out-cross-validation rounds. Conclusion and significance: Our methods can enable tracking of cardiorespiratory phases without additional hardware and reconstruction of respiration-free single cardiac-cycle videos at a much higher temporal resolution.

Original languageEnglish (US)
Article number8345790
Pages (from-to)72-79
Number of pages8
JournalIEEE Transactions on Biomedical Engineering
Volume66
Issue number1
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Electrocardiography
Ultrasonics
Hardware
Echocardiography
Time series
Animals

Keywords

  • cardiac
  • echocardiography
  • gating
  • phase estimation
  • temporal super-resolution
  • Ultrasound

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Chittajallu, D. R., McCormick, M., Gerber, S., Czernuszewicz, T. J., Gessner, R., Willis, M., ... Aylward, S. R. (2019). Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound. IEEE Transactions on Biomedical Engineering, 66(1), 72-79. [8345790]. https://doi.org/10.1109/TBME.2018.2823279

Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound. / Chittajallu, Deepak Roy; McCormick, Matthew; Gerber, Samuel; Czernuszewicz, Tomasz J.; Gessner, Ryan; Willis, Monte; Niethammer, Marc; Kwitt, Roland; Aylward, Stephen R.

In: IEEE Transactions on Biomedical Engineering, Vol. 66, No. 1, 8345790, 01.01.2019, p. 72-79.

Research output: Contribution to journalArticle

Chittajallu, DR, McCormick, M, Gerber, S, Czernuszewicz, TJ, Gessner, R, Willis, M, Niethammer, M, Kwitt, R & Aylward, SR 2019, 'Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound', IEEE Transactions on Biomedical Engineering, vol. 66, no. 1, 8345790, pp. 72-79. https://doi.org/10.1109/TBME.2018.2823279
Chittajallu, Deepak Roy ; McCormick, Matthew ; Gerber, Samuel ; Czernuszewicz, Tomasz J. ; Gessner, Ryan ; Willis, Monte ; Niethammer, Marc ; Kwitt, Roland ; Aylward, Stephen R. / Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound. In: IEEE Transactions on Biomedical Engineering. 2019 ; Vol. 66, No. 1. pp. 72-79.
@article{cee0ab2664a7407c94e07330d678a7a3,
title = "Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound",
abstract = "Objective: Ultrasound is an effective tool for rapid noninvasive assessment of cardiac structure and function. Determining the cardiorespiratory phases of each frame in the ultrasound video and capturing the cardiac function at a much higher temporal resolution are essential in many applications. Fulfilling these requirements is particularly challenging in preclinical studies involving small animals with high cardiorespiratory rates, requiring cumbersome and expensive specialized hardware. Methods: We present a novel method for the retrospective estimation of cardiorespiratory phases directly from the ultrasound videos. It transforms the videos into a univariate time series preserving the evidence of periodic cardiorespiratory motion, decouples the signatures of cardiorespiratory motion with a trend extraction technique, and estimates the cardiorespiratory phases using a Hilbert transform approach. We also present a robust nonparametric regression technique for respiratory gating and a novel kernel-regression model for reconstructing images at any cardiac phase facilitating temporal superresolution. Results: We validated our methods using two-dimensional echocardiography videos and electrocardiogram (ECG) recordings of six mice. Our cardiac phase estimation method provides accurate phase estimates with a mean-phase-error range of 3{\%}-6{\%} against ECG derived phase and outperforms three previously published methods in locating ECGs R-wave peak frames with a mean-frame-error range of 0.73-1.36. Our kernel-regression model accurately reconstructs images at any cardiac phase with a mean-normalized-correlation range of 0.81-0.85 over 50 leave-one-out-cross-validation rounds. Conclusion and significance: Our methods can enable tracking of cardiorespiratory phases without additional hardware and reconstruction of respiration-free single cardiac-cycle videos at a much higher temporal resolution.",
keywords = "cardiac, echocardiography, gating, phase estimation, temporal super-resolution, Ultrasound",
author = "Chittajallu, {Deepak Roy} and Matthew McCormick and Samuel Gerber and Czernuszewicz, {Tomasz J.} and Ryan Gessner and Monte Willis and Marc Niethammer and Roland Kwitt and Aylward, {Stephen R.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/TBME.2018.2823279",
language = "English (US)",
volume = "66",
pages = "72--79",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Image-Based Methods for Phase Estimation, Gating, and Temporal Superresolution of Cardiac Ultrasound

AU - Chittajallu, Deepak Roy

AU - McCormick, Matthew

AU - Gerber, Samuel

AU - Czernuszewicz, Tomasz J.

AU - Gessner, Ryan

AU - Willis, Monte

AU - Niethammer, Marc

AU - Kwitt, Roland

AU - Aylward, Stephen R.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Objective: Ultrasound is an effective tool for rapid noninvasive assessment of cardiac structure and function. Determining the cardiorespiratory phases of each frame in the ultrasound video and capturing the cardiac function at a much higher temporal resolution are essential in many applications. Fulfilling these requirements is particularly challenging in preclinical studies involving small animals with high cardiorespiratory rates, requiring cumbersome and expensive specialized hardware. Methods: We present a novel method for the retrospective estimation of cardiorespiratory phases directly from the ultrasound videos. It transforms the videos into a univariate time series preserving the evidence of periodic cardiorespiratory motion, decouples the signatures of cardiorespiratory motion with a trend extraction technique, and estimates the cardiorespiratory phases using a Hilbert transform approach. We also present a robust nonparametric regression technique for respiratory gating and a novel kernel-regression model for reconstructing images at any cardiac phase facilitating temporal superresolution. Results: We validated our methods using two-dimensional echocardiography videos and electrocardiogram (ECG) recordings of six mice. Our cardiac phase estimation method provides accurate phase estimates with a mean-phase-error range of 3%-6% against ECG derived phase and outperforms three previously published methods in locating ECGs R-wave peak frames with a mean-frame-error range of 0.73-1.36. Our kernel-regression model accurately reconstructs images at any cardiac phase with a mean-normalized-correlation range of 0.81-0.85 over 50 leave-one-out-cross-validation rounds. Conclusion and significance: Our methods can enable tracking of cardiorespiratory phases without additional hardware and reconstruction of respiration-free single cardiac-cycle videos at a much higher temporal resolution.

AB - Objective: Ultrasound is an effective tool for rapid noninvasive assessment of cardiac structure and function. Determining the cardiorespiratory phases of each frame in the ultrasound video and capturing the cardiac function at a much higher temporal resolution are essential in many applications. Fulfilling these requirements is particularly challenging in preclinical studies involving small animals with high cardiorespiratory rates, requiring cumbersome and expensive specialized hardware. Methods: We present a novel method for the retrospective estimation of cardiorespiratory phases directly from the ultrasound videos. It transforms the videos into a univariate time series preserving the evidence of periodic cardiorespiratory motion, decouples the signatures of cardiorespiratory motion with a trend extraction technique, and estimates the cardiorespiratory phases using a Hilbert transform approach. We also present a robust nonparametric regression technique for respiratory gating and a novel kernel-regression model for reconstructing images at any cardiac phase facilitating temporal superresolution. Results: We validated our methods using two-dimensional echocardiography videos and electrocardiogram (ECG) recordings of six mice. Our cardiac phase estimation method provides accurate phase estimates with a mean-phase-error range of 3%-6% against ECG derived phase and outperforms three previously published methods in locating ECGs R-wave peak frames with a mean-frame-error range of 0.73-1.36. Our kernel-regression model accurately reconstructs images at any cardiac phase with a mean-normalized-correlation range of 0.81-0.85 over 50 leave-one-out-cross-validation rounds. Conclusion and significance: Our methods can enable tracking of cardiorespiratory phases without additional hardware and reconstruction of respiration-free single cardiac-cycle videos at a much higher temporal resolution.

KW - cardiac

KW - echocardiography

KW - gating

KW - phase estimation

KW - temporal super-resolution

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85045986538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045986538&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2823279

DO - 10.1109/TBME.2018.2823279

M3 - Article

C2 - 29993406

AN - SCOPUS:85045986538

VL - 66

SP - 72

EP - 79

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 1

M1 - 8345790

ER -