Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction

Jo Schlemper; Jinming Duan; Cheng Ouyang; Chen Qin; Jose Caballero; Joseph V. Hajnal; Daniel Rueckert

Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction

Jo Schlemper, Jinming Duan, Cheng Ouyang, Chen Qin, Jose Caballero, Joseph V. Hajnal, Daniel Rueckert

School of Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract / Description of output

We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the state of the art both quantitatively and qualitatively.

Original language	English
Publication status	Published - 25 Sept 2019
Event	ISMRM 27th Annual Meeting & Exhibition, 11-16 May 2019 - alais des congrès de Montréal, 1001 Place Jean-Paul-Riopelle, Montreal, Canada Duration: 11 May 2019 → 16 May 2019 https://www.ismrm.org/19m/

Conference

Conference	ISMRM 27th Annual Meeting & Exhibition, 11-16 May 2019
Country/Territory	Canada
City	Montreal
Period	11/05/19 → 16/05/19
Internet address	https://www.ismrm.org/19m/

Keywords / Materials (for Non-textual outputs)

eess.IV
cs.CV
cs.LG
stat.ML

Access to Document

1909.11795v1

https://arxiv.org/abs/1909.11795

Cite this

@conference{fe402ea352564115baecb7258720b38a,

title = "Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction",

abstract = " We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the state of the art both quantitatively and qualitatively. ",

keywords = "eess.IV, cs.CV, cs.LG, stat.ML",

author = "Jo Schlemper and Jinming Duan and Cheng Ouyang and Chen Qin and Jose Caballero and Hajnal, {Joseph V.} and Daniel Rueckert",

note = "Presented at ISMRM 27th Annual Meeting & Exhibition (Abstract #4663); ISMRM 27th Annual Meeting & Exhibition, 11-16 May 2019 ; Conference date: 11-05-2019 Through 16-05-2019",

year = "2019",

month = sep,

day = "25",

language = "English",

url = "https://www.ismrm.org/19m/",

}

TY - CONF

T1 - Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction

AU - Schlemper, Jo

AU - Duan, Jinming

AU - Ouyang, Cheng

AU - Qin, Chen

AU - Caballero, Jose

AU - Hajnal, Joseph V.

AU - Rueckert, Daniel

N1 - Presented at ISMRM 27th Annual Meeting & Exhibition (Abstract #4663)

PY - 2019/9/25

Y1 - 2019/9/25

N2 - We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the state of the art both quantitatively and qualitatively.

AB - We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the state of the art both quantitatively and qualitatively.

KW - eess.IV

KW - cs.CV

KW - cs.LG

KW - stat.ML

M3 - Paper

T2 - ISMRM 27th Annual Meeting & Exhibition, 11-16 May 2019

Y2 - 11 May 2019 through 16 May 2019

ER -

Data consistency networks for (calibration-less) accelerated parallel MR image reconstruction

Abstract / Description of output

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this