Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation

Qing Zou; Abdul Haseeb Ahmed; Sanja Dzelebdzic; Tarique Hussain

doi:10.3390/app13042281

Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation

Qing Zou, Abdul Haseeb Ahmed, Sanja Dzelebdzic, Tarique Hussain

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t space measurements. We propose implementing the feature map and kernel function in the kernel method using CNNs. The parameters of the CNNs are learned from specific-subject data directly. Comparisons with state-of-the-art kernel methods show improved performance of the proposed deep kernel method.

Original language	English (US)
Article number	2281
Journal	Applied Sciences (Switzerland)
Volume	13
Issue number	4
DOIs	https://doi.org/10.3390/app13042281
State	Published - Feb 2023

Keywords

convolutional neural networks
image reconstruction
kernel method
real-time cardiac MRI

ASJC Scopus subject areas

General Materials Science
Instrumentation
General Engineering
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes

Access to Document

10.3390/app13042281

Cite this

@article{6c6258aabdfa47c5a5426f6973595126,

title = "Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation",

abstract = "Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t space measurements. We propose implementing the feature map and kernel function in the kernel method using CNNs. The parameters of the CNNs are learned from specific-subject data directly. Comparisons with state-of-the-art kernel methods show improved performance of the proposed deep kernel method.",

keywords = "convolutional neural networks, image reconstruction, kernel method, real-time cardiac MRI",

author = "Qing Zou and Ahmed, {Abdul Haseeb} and Sanja Dzelebdzic and Tarique Hussain",

note = "Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = feb,

doi = "10.3390/app13042281",

language = "English (US)",

volume = "13",

journal = "Applied Sciences (Switzerland)",

issn = "2076-3417",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "4",

}

TY - JOUR

T1 - Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation

AU - Zou, Qing

AU - Ahmed, Abdul Haseeb

AU - Dzelebdzic, Sanja

AU - Hussain, Tarique

PY - 2023/2

Y1 - 2023/2

N2 - Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t space measurements. We propose implementing the feature map and kernel function in the kernel method using CNNs. The parameters of the CNNs are learned from specific-subject data directly. Comparisons with state-of-the-art kernel methods show improved performance of the proposed deep kernel method.

AB - Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t space measurements. We propose implementing the feature map and kernel function in the kernel method using CNNs. The parameters of the CNNs are learned from specific-subject data directly. Comparisons with state-of-the-art kernel methods show improved performance of the proposed deep kernel method.

KW - convolutional neural networks

KW - image reconstruction

KW - kernel method

KW - real-time cardiac MRI

UR - http://www.scopus.com/inward/record.url?scp=85149300614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85149300614&partnerID=8YFLogxK

U2 - 10.3390/app13042281

DO - 10.3390/app13042281

M3 - Article

AN - SCOPUS:85149300614

SN - 2076-3417

VL - 13

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

IS - 4

M1 - 2281

ER -

Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this