dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

Jo Schlemper; Ilkay Oksuz; James R. Clough; Jinming Duan; Andrew P. King; Julia A. Schnabel; Joseph V. Hajnal; Daniel Rueckert

dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

Jo Schlemper, Ilkay Oksuz, James R. Clough, Jinming Duan, Andrew P. King, Julia A. Schnabel, Joseph V. Hajnal, Daniel Rueckert

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

42 Downloads (Pure)

Abstract

AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters.

Original language	Undefined/Unknown
Journal	conference abstracts of ISMRM
Publication status	Published - 24 Sept 2019

Keywords

cs.LG
eess.IV
stat.ML

Access to Document

1909.10995v2

Cite this

@article{2611da768ada4610bbbc66854baa0bf7,

title = "dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance",

abstract = "AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters. ",

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

author = "Jo Schlemper and Ilkay Oksuz and Clough, {James R.} and Jinming Duan and King, {Andrew P.} and Schnabel, {Julia A.} and Hajnal, {Joseph V.} and Daniel Rueckert",

note = "Presented at ISMRM 27th Annual Meeting & Exhibition (Abstract #658)",

year = "2019",

month = sep,

day = "24",

language = "Undefined/Unknown",

journal = "conference abstracts of ISMRM",

}

TY - JOUR

T1 - dAUTOMAP

T2 - decomposing AUTOMAP to achieve scalability and enhance performance

AU - Schlemper, Jo

AU - Oksuz, Ilkay

AU - Clough, James R.

AU - Duan, Jinming

AU - King, Andrew P.

AU - Schnabel, Julia A.

AU - Hajnal, Joseph V.

AU - Rueckert, Daniel

N1 - Presented at ISMRM 27th Annual Meeting & Exhibition (Abstract #658)

PY - 2019/9/24

Y1 - 2019/9/24

N2 - AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters.

AB - AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters.

KW - cs.LG

KW - eess.IV

KW - stat.ML

M3 - Article

JO - conference abstracts of ISMRM

JF - conference abstracts of ISMRM

ER -