Hyperfine Operations, Inc.

Prantik Kundu

Michal Sofka

Laura Sacolick

Hadrien A Dyvorne

Rafael O'Halloran

Jo Schlemper

Carole Lazarus

Jonathan Marc Rothberg

Seyed Sadegh Mohseni Salehi

Ziyi Wang

Seyed Sadegh Moshen Salehi

Michael Stephen Poole

Eddy B Boskamp

Michael Twieg

Mark Joseph Tuccillo

Khan Mohammad Siddiqui

Seyed Sadegh Mosheni Salehi

Sunli Tang

Tianrui Luo

Neel Dey

Techniques for denoising a magnetic resonance (MR) image are provided, including: obtaining a noisy MR image; denoising the noisy MR image of the subject using a denoising neural network model, and outputting a denoised MR image. The denoising neural network model is trained by: generating first training data for training a first neural network model to denoise MR images by generating a first plurality of noisy MR images using clean MR data associated with a source domain and first MR noise data associated with the target domain; training the first neural network model using the first training data; generating training data for training the denoising neural network model by applying the first neural network model to a second plurality of noisy MR images and generating a plurality of denoised MR images; and training the denoising neural network model using the training data for training the denoising neural network model.

Deep learning methods for noise suppression in medical imaging

A magnetic resonance imaging (MRI) system, comprising: a magnetics system comprising: a Bmagnet configured to provide a Bfield for the MRI system; gradient coils configured to provide gradient fields for the MRI system; and at least one RF coil configured to detect magnetic resonance (MR) signals; and a controller configured to: control the magnetics system to acquire MR spatial frequency data using non-Cartesian sampling; and generate an MR image from the acquired MR spatial frequency data using a neural network model comprising one or more neural network blocks including a first neural network block, wherein the first neural network block is configured to perform data consistency processing using a non-uniform Fourier transformation.

Deep learning techniques for magnetic resonance image reconstruction

A device and method for detecting motion and position of a patient positioned within a magnetic resonance imaging system, the device including at least one sensor configured to be capacitively coupled to the patient during magnetic resonance imaging. The method includes, while a patient is positioned within a magnetic resonance imaging system, measuring a reflected power value indicative of an amount of power reflected by the at least one sensor in response to being driven by at least one RF signal, and determining, using the reflected power value, whether the patient has moved.

Systems and methods for detecting patient motion during magnetic resonance imaging

Techniques are provided for imaging a subject. A magnetic resonance imaging (MRI) system may use at least one RF coil to generate an initial MR data set for an initial image of the subject. The MRI system may use the initial MR image to determine a difference in orientation between a current orientation of the subject in the initial MR image and a target orientation of the subject. The MRI system may use the determined difference in orientation to determine an adjustment to a gradient pulse sequence for controlling at least one gradient coil. The MRI system may apply the determined adjustment to the gradient pulse sequence to obtain an adjusted gradient pulse sequence. The MRI system may generate an adjusted MR data set using the adjusted gradient pulse sequence, and a second MR image of the subject using the adjusted MR data set.

Systems and methods for performing magnetic resonance imaging with reduced operator interaction

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.

Deep learning techniques for suppressing artefacts in magnetic resonance images

Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques include: obtaining input MR spatial frequency data obtained by imaging the subject using the MRI system; generating an MR image of the subject from the input MR spatial frequency data using a neural network model comprising: a pre-reconstruction neural network configured to process the input MR spatial frequency data; a reconstruction neural network configured to generate at least one initial image of the subject from output of the pre-reconstruction neural network; and a post-reconstruction neural network configured to generate the MR image of the subject from the at least one initial image of the subject.

Deep learning techniques for generating magnetic resonance images from spatial frequency data

Growing community of inventors

Branford, CT, United States of America

Prantik Kundu