Fully automated myocardial strain estimation from cine MRI using convolutional neural networks

Esther Puyol-Anton; Bram Ruijsink; Wenjia Bai; Helene Langet; Mathieu De Craene; Julia A. Schnabel; Paolo Piro; Andrew P. King; Matthew Sinclair

doi:10.1109/ISBI.2018.8363772

Fully automated myocardial strain estimation from cine MRI using convolutional neural networks

Esther Puyol-Anton, Bram Ruijsink, Wenjia Bai, Helene Langet, Mathieu De Craene, Julia A. Schnabel, Paolo Piro, Andrew P. King, Matthew Sinclair

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

20 Citations (Scopus)

538 Downloads (Pure)

Abstract

Cardiovascular magnetic resonance myocardial feature tracking (CMR-FT) is a promising method for quantification of cardiac function from standard steady-state free precession (SSFP) images. However, currently available techniques require operator dependent and time-consuming manual intervention, limiting reproducibility and clinical use. In this paper, we propose a fully automated pipeline to compute left ventricular (LV) longitudinal and radial strain from 2- and 4-chamber cine acquisitions, and LV circumferential and radial strain from the short-axis imaging. The method employs a convolutional neural network to automatically segment the myocardium, followed by feature tracking and strain estimation. Experiments are performed using 40 healthy volunteers and 40 ischemic patients from the UK Biobank dataset. Results show that our method obtained strain values that were in excellent agreement with the commercially available clinical CMR-FT software CVI₄₂ (Circle Cardiovascular Imaging, Calgary, Canada).

Original language	English
Title of host publication	2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Publisher	IEEE Computer Society
Pages	1139-1143
Number of pages	5
Volume	2018-April
ISBN (Electronic)	9781538636367
DOIs	https://doi.org/10.1109/ISBI.2018.8363772
Publication status	Published - 23 May 2018
Event	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States Duration: 4 Apr 2018 → 7 Apr 2018

Conference

Conference	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Country/Territory	United States
City	Washington
Period	4/04/2018 → 7/04/2018

Keywords

Automatic pipeline
Machine learning
MRI
Myocardial Strain

Access to Document

10.1109/ISBI.2018.8363772

Fully automated myocardial strain_PUYOL-ANTON_Published23May2018_GREEN AAM
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Accepted author manuscript, 701 KB

Cite this

Puyol-Anton, E., Ruijsink, B., Bai, W., Langet, H., De Craene, M., Schnabel, J. A., Piro, P., King, A. P., & Sinclair, M. (2018). Fully automated myocardial strain estimation from cine MRI using convolutional neural networks. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 1139-1143). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363772

@inbook{40205dffd4ff4c68853f37db2afbbc5d,

title = "Fully automated myocardial strain estimation from cine MRI using convolutional neural networks",

abstract = "Cardiovascular magnetic resonance myocardial feature tracking (CMR-FT) is a promising method for quantification of cardiac function from standard steady-state free precession (SSFP) images. However, currently available techniques require operator dependent and time-consuming manual intervention, limiting reproducibility and clinical use. In this paper, we propose a fully automated pipeline to compute left ventricular (LV) longitudinal and radial strain from 2- and 4-chamber cine acquisitions, and LV circumferential and radial strain from the short-axis imaging. The method employs a convolutional neural network to automatically segment the myocardium, followed by feature tracking and strain estimation. Experiments are performed using 40 healthy volunteers and 40 ischemic patients from the UK Biobank dataset. Results show that our method obtained strain values that were in excellent agreement with the commercially available clinical CMR-FT software CVI42 (Circle Cardiovascular Imaging, Calgary, Canada).",

keywords = "Automatic pipeline, Machine learning, MRI, Myocardial Strain",

author = "Esther Puyol-Anton and Bram Ruijsink and Wenjia Bai and Helene Langet and {De Craene}, Mathieu and Schnabel, {Julia A.} and Paolo Piro and King, {Andrew P.} and Matthew Sinclair",

year = "2018",

month = may,

day = "23",

doi = "10.1109/ISBI.2018.8363772",

language = "English",

volume = "2018-April",

pages = "1139--1143",

booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",

publisher = "IEEE Computer Society",

note = "15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 ; Conference date: 04-04-2018 Through 07-04-2018",

}

Puyol-Anton, E , Ruijsink, B, Bai, W, Langet, H, De Craene, M, Schnabel, JA, Piro, P, King, AP & Sinclair, M 2018, Fully automated myocardial strain estimation from cine MRI using convolutional neural networks. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 1139-1143, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/04/2018. https://doi.org/10.1109/ISBI.2018.8363772

Fully automated myocardial strain estimation from cine MRI using convolutional neural networks. / Puyol-Anton, Esther ; Ruijsink, Bram; Bai, Wenjia et al.
2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 1139-1143.

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

TY - CHAP

T1 - Fully automated myocardial strain estimation from cine MRI using convolutional neural networks

AU - Puyol-Anton, Esther

AU - Ruijsink, Bram

AU - Bai, Wenjia

AU - Langet, Helene

AU - De Craene, Mathieu

AU - Schnabel, Julia A.

AU - Piro, Paolo

AU - King, Andrew P.

AU - Sinclair, Matthew

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Cardiovascular magnetic resonance myocardial feature tracking (CMR-FT) is a promising method for quantification of cardiac function from standard steady-state free precession (SSFP) images. However, currently available techniques require operator dependent and time-consuming manual intervention, limiting reproducibility and clinical use. In this paper, we propose a fully automated pipeline to compute left ventricular (LV) longitudinal and radial strain from 2- and 4-chamber cine acquisitions, and LV circumferential and radial strain from the short-axis imaging. The method employs a convolutional neural network to automatically segment the myocardium, followed by feature tracking and strain estimation. Experiments are performed using 40 healthy volunteers and 40 ischemic patients from the UK Biobank dataset. Results show that our method obtained strain values that were in excellent agreement with the commercially available clinical CMR-FT software CVI42 (Circle Cardiovascular Imaging, Calgary, Canada).

AB - Cardiovascular magnetic resonance myocardial feature tracking (CMR-FT) is a promising method for quantification of cardiac function from standard steady-state free precession (SSFP) images. However, currently available techniques require operator dependent and time-consuming manual intervention, limiting reproducibility and clinical use. In this paper, we propose a fully automated pipeline to compute left ventricular (LV) longitudinal and radial strain from 2- and 4-chamber cine acquisitions, and LV circumferential and radial strain from the short-axis imaging. The method employs a convolutional neural network to automatically segment the myocardium, followed by feature tracking and strain estimation. Experiments are performed using 40 healthy volunteers and 40 ischemic patients from the UK Biobank dataset. Results show that our method obtained strain values that were in excellent agreement with the commercially available clinical CMR-FT software CVI42 (Circle Cardiovascular Imaging, Calgary, Canada).

KW - Automatic pipeline

KW - Machine learning

KW - MRI

KW - Myocardial Strain

UR - http://www.scopus.com/inward/record.url?scp=85048092290&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363772

DO - 10.1109/ISBI.2018.8363772

M3 - Conference paper

AN - SCOPUS:85048092290

VL - 2018-April

SP - 1139

EP - 1143

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

T2 - 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018

Y2 - 4 April 2018 through 7 April 2018

ER -

Fully automated myocardial strain estimation from cine MRI using convolutional neural networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this