US 12,105,173 B2
Self ensembling techniques for generating magnetic resonance images from spatial frequency data
Jo Schlemper, Long Island City, NY (US); Seyed Sadegh Mohseni Salehi, Bloomfield, NJ (US); and Michal Sofka, Princeton, NJ (US)
Assigned to Hyperfine Operations, Inc., Guilford, CT (US)
Filed by Hyperfine Operations, Inc., Guilford, CT (US)
Filed on May 5, 2023, as Appl. No. 18/312,654.
Application 18/312,654 is a continuation of application No. 17/478,127, filed on Sep. 17, 2021, granted, now 11,681,000.
Application 17/478,127 is a continuation of application No. 16/817,454, filed on Mar. 12, 2020, granted, now 11,185,249.
Claims priority of provisional application 62/926,890, filed on Oct. 28, 2019.
Claims priority of provisional application 62/820,119, filed on Mar. 18, 2019.
Claims priority of provisional application 62/818,148, filed on Mar. 14, 2019.
Prior Publication US 2024/0118359 A1, Apr. 11, 2024
Int. Cl. G01R 33/561 (2006.01); A61B 5/055 (2006.01); G01R 33/36 (2006.01); G01R 33/383 (2006.01); G01R 33/44 (2006.01); G01R 33/56 (2006.01); G06F 18/2134 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 3/082 (2023.01); G06T 3/60 (2006.01); G06T 7/00 (2017.01); G06T 7/262 (2017.01); G06T 7/38 (2017.01); G06T 11/00 (2006.01); G06V 10/30 (2022.01); G06V 10/42 (2022.01); G06V 10/44 (2022.01); G06V 10/52 (2022.01); G06V 10/75 (2022.01); G06V 10/82 (2022.01); G06V 10/88 (2022.01); G16H 30/40 (2018.01)
CPC G01R 33/5611 (2013.01) [A61B 5/055 (2013.01); G01R 33/36 (2013.01); G01R 33/383 (2013.01); G01R 33/445 (2013.01); G01R 33/5608 (2013.01); G06F 18/21347 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/082 (2013.01); G06T 3/60 (2013.01); G06T 7/0012 (2013.01); G06T 7/262 (2017.01); G06T 7/38 (2017.01); G06T 11/006 (2013.01); G06T 11/008 (2013.01); G06V 10/30 (2022.01); G06V 10/431 (2022.01); G06V 10/454 (2022.01); G06V 10/52 (2022.01); G06V 10/7515 (2022.01); G06V 10/82 (2022.01); G06V 10/89 (2022.01); G06V 10/92 (2022.01); G16H 30/40 (2018.01); G06T 2207/10088 (2013.01); G06T 2207/20056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20182 (2013.01); G06T 2207/20216 (2013.01); G06T 2207/20224 (2013.01); G06T 2207/30016 (2013.01); G06T 2210/41 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating, from magnitude MR images, training data for training a neural network model to process data to be collected by a target MRI system, the training data comprising the magnitude MR images and synthetic spatial frequency data generated from the magnitude MR images in part by using characteristics of the target MRI system, the method comprising:
using at least one computer hardware processor to perform:
(A) obtaining a reference MR volume comprising one or more magnitude MR images;
(B) updating the reference MR volume, using a target field of view and/or target image resolution for the target MRI system, to obtain an updated MR volume;
(C) generating synthetic phase and adding the generated synthetic phase to the updated MR volume to obtain a target MR volume; and
(D) generating, from the target MR volume and using one or more of the characteristics of the target MRI system, multiple sets of spatial frequency data to be used as part of the training data for training the neural network model to process the data to be collected by the target MRI system.