Magnetic resonance fingerprinting using recurrent neural networks

Ilkay Oksuz; Gastao Cruz; James Clough; Aurelien Bustin; Nicolo Fuin; Rene M. Botnar; Claudia Prieto; Andrew P. King; Julia A. Schnabel

doi:10.1109/ISBI.2019.8759502

Magnetic resonance fingerprinting using recurrent neural networks

Ilkay Oksuz, Gastao Cruz, James Clough, Aurelien Bustin, Nicolo Fuin, Rene M. Botnar, Claudia Prieto, Andrew P. King, Julia A. Schnabel

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

32 Citations (Scopus)

Abstract

Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and requires high computational time. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is reduced compared to dictionary-matching based approach.

Original language	English
Title of host publication	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
Pages	1537-1540
Number of pages	4
Volume	2019-April
ISBN (Electronic)	9781538636411
DOIs	https://doi.org/10.1109/ISBI.2019.8759502
Publication status	Published - 1 Apr 2019
Event	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy Duration: 8 Apr 2019 → 11 Apr 2019

Conference

Conference	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/Territory	Italy
City	Venice
Period	8/04/2019 → 11/04/2019

Keywords

Gru
Lstm
Magnetic resonance fingerprinting
Parameter mapping
Recurrent neural networks

Access to Document

10.1109/ISBI.2019.8759502

Cite this

Oksuz, I., Cruz, G., Clough, J., Bustin, A., Fuin, N., Botnar, R. M., Prieto, C., King, A. P., & Schnabel, J. A. (2019). Magnetic resonance fingerprinting using recurrent neural networks. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (Vol. 2019-April, pp. 1537-1540). Article 8759502 IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759502

@inbook{439b4dec45e84c16bdf9289a4ff2577e,

title = "Magnetic resonance fingerprinting using recurrent neural networks",

abstract = "Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and requires high computational time. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is reduced compared to dictionary-matching based approach.",

keywords = "Gru, Lstm, Magnetic resonance fingerprinting, Parameter mapping, Recurrent neural networks",

author = "Ilkay Oksuz and Gastao Cruz and James Clough and Aurelien Bustin and Nicolo Fuin and Botnar, {Rene M.} and Claudia Prieto and King, {Andrew P.} and Schnabel, {Julia A.}",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/ISBI.2019.8759502",

language = "English",

volume = "2019-April",

pages = "1537--1540",

booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

note = "16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

}

Oksuz, I , Cruz, G , Clough, J , Bustin, A , Fuin, N , Botnar, RM , Prieto, C , King, AP & Schnabel, JA 2019, Magnetic resonance fingerprinting using recurrent neural networks. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. vol. 2019-April, 8759502, IEEE Computer Society, pp. 1537-1540, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 8/04/2019. https://doi.org/10.1109/ISBI.2019.8759502

TY - CHAP

T1 - Magnetic resonance fingerprinting using recurrent neural networks

AU - Oksuz, Ilkay

AU - Cruz, Gastao

AU - Clough, James

AU - Bustin, Aurelien

AU - Fuin, Nicolo

AU - Botnar, Rene M.

AU - Prieto, Claudia

AU - King, Andrew P.

AU - Schnabel, Julia A.

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and requires high computational time. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is reduced compared to dictionary-matching based approach.

AB - Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and requires high computational time. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is reduced compared to dictionary-matching based approach.

KW - Gru

KW - Lstm

KW - Magnetic resonance fingerprinting

KW - Parameter mapping

KW - Recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85073892391&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759502

DO - 10.1109/ISBI.2019.8759502

M3 - Conference paper

AN - SCOPUS:85073892391

VL - 2019-April

SP - 1537

EP - 1540

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019

Y2 - 8 April 2019 through 11 April 2019

ER -

Magnetic resonance fingerprinting using recurrent neural networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this