dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

52 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 languageEnglish
Title of host publicationProceedings of the ISMRM 27th Annual Meeting & Exhibition
Publication statusPublished - 26 Apr 2019
EventISMRM 27th Annual meeting & exhibition - Montreal, Canada
Duration: 11 May 201916 May 2019

Publication series

NameProceedings of the International Society for Magnetic Resonance in Medicine Scientific Meeting and Exhibition
ISSN (Electronic)1545-4428

Conference

ConferenceISMRM 27th Annual meeting & exhibition
Country/TerritoryCanada
CityMontreal
Period11/05/1916/05/19

Keywords

  • cs.LG
  • eess.IV
  • stat.ML

Fingerprint

Dive into the research topics of 'dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance'. Together they form a unique fingerprint.

Cite this