Deep Kernel Method for Dynamic MRI Reconstruction

Qing Zou; Sanja Dzelebdzic; Tarique Hussain

doi:10.1109/ISBI53787.2023.10230467

Deep Kernel Method for Dynamic MRI Reconstruction

Qing Zou, Sanja Dzelebdzic, Tarique Hussain

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce a deep kernel model for the recovery of real-time dynamic MRI from highly undersampled measurements. The proposed scheme uses the cascade of two deep convolutional neural networks (CNN) for the kernel representation of images. Unlike the supervised CNN approaches for image reconstructions that require extensive fully-sampled training data for learning the network, the parameters of the two CNNs in the proposed method are learned from the undersampled measurements directly in this work. The main benefits of the proposed scheme are (a) the elimination of the empirical choice of the feature map and kernel function in the kernel method, and (b) the unsupervised nature of the proposed framework.

Original language	English (US)
Title of host publication	2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665473583
DOIs	https://doi.org/10.1109/ISBI53787.2023.10230467
State	Published - 2023
Event	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 - Cartagena, Colombia Duration: Apr 18 2023 → Apr 21 2023

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2023-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Country/Territory	Colombia
City	Cartagena
Period	4/18/23 → 4/21/23

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI53787.2023.10230467

Cite this

Zou, Q, Dzelebdzic, S & Hussain, T 2023, Deep Kernel Method for Dynamic MRI Reconstruction. in 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. Proceedings - International Symposium on Biomedical Imaging, vol. 2023-April, IEEE Computer Society, 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023, Cartagena, Colombia, 4/18/23. https://doi.org/10.1109/ISBI53787.2023.10230467

@inproceedings{6196209fd1924becaf6361c1b5cee1b5,

title = "Deep Kernel Method for Dynamic MRI Reconstruction",

abstract = "We introduce a deep kernel model for the recovery of real-time dynamic MRI from highly undersampled measurements. The proposed scheme uses the cascade of two deep convolutional neural networks (CNN) for the kernel representation of images. Unlike the supervised CNN approaches for image reconstructions that require extensive fully-sampled training data for learning the network, the parameters of the two CNNs in the proposed method are learned from the undersampled measurements directly in this work. The main benefits of the proposed scheme are (a) the elimination of the empirical choice of the feature map and kernel function in the kernel method, and (b) the unsupervised nature of the proposed framework.",

author = "Qing Zou and Sanja Dzelebdzic and Tarique Hussain",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1109/ISBI53787.2023.10230467",

language = "English (US)",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

booktitle = "2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023",

}

TY - GEN

T1 - Deep Kernel Method for Dynamic MRI Reconstruction

AU - Zou, Qing

AU - Dzelebdzic, Sanja

AU - Hussain, Tarique

PY - 2023

Y1 - 2023

N2 - We introduce a deep kernel model for the recovery of real-time dynamic MRI from highly undersampled measurements. The proposed scheme uses the cascade of two deep convolutional neural networks (CNN) for the kernel representation of images. Unlike the supervised CNN approaches for image reconstructions that require extensive fully-sampled training data for learning the network, the parameters of the two CNNs in the proposed method are learned from the undersampled measurements directly in this work. The main benefits of the proposed scheme are (a) the elimination of the empirical choice of the feature map and kernel function in the kernel method, and (b) the unsupervised nature of the proposed framework.

AB - We introduce a deep kernel model for the recovery of real-time dynamic MRI from highly undersampled measurements. The proposed scheme uses the cascade of two deep convolutional neural networks (CNN) for the kernel representation of images. Unlike the supervised CNN approaches for image reconstructions that require extensive fully-sampled training data for learning the network, the parameters of the two CNNs in the proposed method are learned from the undersampled measurements directly in this work. The main benefits of the proposed scheme are (a) the elimination of the empirical choice of the feature map and kernel function in the kernel method, and (b) the unsupervised nature of the proposed framework.

UR - http://www.scopus.com/inward/record.url?scp=85172117110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85172117110&partnerID=8YFLogxK

U2 - 10.1109/ISBI53787.2023.10230467

DO - 10.1109/ISBI53787.2023.10230467

M3 - Conference contribution

AN - SCOPUS:85172117110

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023

PB - IEEE Computer Society

T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023

Y2 - 18 April 2023 through 21 April 2023

ER -

Deep Kernel Method for Dynamic MRI Reconstruction

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this