Spatio-temporal regularization for deep MR Fingerprinting

Mohammad Golbabaee, Dongdong Chen, Marion I. Menzel, Mike Davies, Pedro A. Gómez

Research output: Contribution to conferencePaper

Abstract

We study a deep learning approach to address the heavy storage and computation requirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprinting (MRF) reconstruction. The MRF-Net provides a piece-wise affine approximation to the (temporal) Bloch response manifold projection. Fed with non-iterated back-projected images, the network alone is unable to fully resolve spatially-correlated artefacts which appear in highly undersampling regimes. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series.
Original languageEnglish
Publication statusPublished - 10 Jul 2019
EventMedical Imaging with Deep Learning - London, UK United Kingdom
Duration: 8 Jul 201910 Jul 2019
https://openreview.net/group?id=MIDL.io/2019/Conference/Abstract

Conference

ConferenceMedical Imaging with Deep Learning
Abbreviated titleMIDL 2019
CountryUK United Kingdom
CityLondon
Period8/07/1910/07/19
Internet address

Cite this

Golbabaee, M., Chen, D., Menzel, M. I., Davies, M., & Gómez, P. A. (2019). Spatio-temporal regularization for deep MR Fingerprinting. Paper presented at Medical Imaging with Deep Learning, London, UK United Kingdom.

Spatio-temporal regularization for deep MR Fingerprinting. / Golbabaee, Mohammad; Chen, Dongdong; Menzel, Marion I.; Davies, Mike; Gómez, Pedro A. .

2019. Paper presented at Medical Imaging with Deep Learning, London, UK United Kingdom.

Research output: Contribution to conferencePaper

Golbabaee, M, Chen, D, Menzel, MI, Davies, M & Gómez, PA 2019, 'Spatio-temporal regularization for deep MR Fingerprinting', Paper presented at Medical Imaging with Deep Learning, London, UK United Kingdom, 8/07/19 - 10/07/19.
Golbabaee M, Chen D, Menzel MI, Davies M, Gómez PA. Spatio-temporal regularization for deep MR Fingerprinting. 2019. Paper presented at Medical Imaging with Deep Learning, London, UK United Kingdom.
Golbabaee, Mohammad ; Chen, Dongdong ; Menzel, Marion I. ; Davies, Mike ; Gómez, Pedro A. . / Spatio-temporal regularization for deep MR Fingerprinting. Paper presented at Medical Imaging with Deep Learning, London, UK United Kingdom.
@conference{9140af23757040de91531c42c480f4c9,
title = "Spatio-temporal regularization for deep MR Fingerprinting",
abstract = "We study a deep learning approach to address the heavy storage and computation requirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprinting (MRF) reconstruction. The MRF-Net provides a piece-wise affine approximation to the (temporal) Bloch response manifold projection. Fed with non-iterated back-projected images, the network alone is unable to fully resolve spatially-correlated artefacts which appear in highly undersampling regimes. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series.",
author = "Mohammad Golbabaee and Dongdong Chen and Menzel, {Marion I.} and Mike Davies and G{\'o}mez, {Pedro A.}",
year = "2019",
month = "7",
day = "10",
language = "English",
note = "Medical Imaging with Deep Learning, MIDL 2019 ; Conference date: 08-07-2019 Through 10-07-2019",
url = "https://openreview.net/group?id=MIDL.io/2019/Conference/Abstract",

}

TY - CONF

T1 - Spatio-temporal regularization for deep MR Fingerprinting

AU - Golbabaee, Mohammad

AU - Chen, Dongdong

AU - Menzel, Marion I.

AU - Davies, Mike

AU - Gómez, Pedro A.

PY - 2019/7/10

Y1 - 2019/7/10

N2 - We study a deep learning approach to address the heavy storage and computation requirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprinting (MRF) reconstruction. The MRF-Net provides a piece-wise affine approximation to the (temporal) Bloch response manifold projection. Fed with non-iterated back-projected images, the network alone is unable to fully resolve spatially-correlated artefacts which appear in highly undersampling regimes. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series.

AB - We study a deep learning approach to address the heavy storage and computation requirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprinting (MRF) reconstruction. The MRF-Net provides a piece-wise affine approximation to the (temporal) Bloch response manifold projection. Fed with non-iterated back-projected images, the network alone is unable to fully resolve spatially-correlated artefacts which appear in highly undersampling regimes. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series.

M3 - Paper

ER -