Patent · US Active

Deep learning techniques for suppressing artefacts in magnetic resonance images

US11789104B2 · kind B2 · utility

1Cited by

94References

17Claims

0Family size

Assignee

Hyperfine Operations, Inc. · US

Inventors

Carole Lazarus · Paris, FR
Prantik Kundu · Branford, US
Sunli Tang · New York, US
Seyed Sadegh Mohseni Salehi · Bloomfield, US
Michal Sofka · Princeton, US
Jo Schlemper · Manhattan, US
Hadrien A. Dyvorne · Branford, US
Rafael O'Halloran · Guilford, US
Laura Sacolick · Madison, US
Michael Stephen Poole · Guilford, US
Jonathan M. Rothberg · Paradise, US

Key dates

Filing date	Aug 15, 2019
Grant date	Oct 17, 2023
Priority date	—
Expiry date	Aug 15, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V2201/031
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques for removing artefacts, such as RF interference and/or noise, from magnetic resonance data. The techniques include: obtaining input magnetic resonance (MR) data using at least one radio-frequency (RF) coil of a magnetic resonance imaging (MRI) system; and generating an MR image from input MR data at least in part by using a neural network model to suppress at least one artefact in the input MR data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.