Hyperfine Operations, Inc.

Carole Lazarus

Hadrien A Dyvorne

Rafael O'Halloran

Laura Sacolick

Michal Sofka

Jo Schlemper

Prantik Kundu

Jonathan Marc Rothberg

Seyed Sadegh Mohseni Salehi

Ziyi Wang

Michael Stephen Poole

Jeremy Christopher Jordan

Eddy B Boskamp

Michael Twieg

Seyed Sadegh Moshen Salehi

Seyed Sadegh Mosheni Salehi

Sunli Tang

A magnetic resonance imaging (MRI) system and method for acquiring magnetic resonance (MR) images using a pulse sequence implementing driven equilibrium and quadratic phase cycling techniques is provided. The method includes, during a pulse repetition period of a pulse sequence and using a quadratic phase cycling scheme, applying a first RF pulse to deflect a net magnetization vector associated with the subject from a longitudinal plane into a transverse plane; after applying the first RF pulse, applying a first sequence of RF pulses each of which flips the net magnetization vector by approximately 180 degrees within the transverse plane; and after applying the first sequence of RF pulses, applying a second RF pulse to deflect the net magnetization vector from the transverse plane to the longitudinal plane.

Systems and methods for low-field fast spin echo 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

Techniques of prospectively compensating for motion of a subject being imaged by an MRI system, the MRI system comprising a plurality of magnetics components including at least one gradient coil and at least one radio-frequency (RF) coil, the techniques comprising: obtaining first spatial frequency data and second spatial frequency data by operating the MRI system in accordance with a pulse sequence, wherein the pulse sequence is associated with a sampling path that includes at least two non-contiguous portions each for sampling a central region of k-space; determining a transformation using a first image obtained using the first spatial frequency data and a second image obtained using the second spatial frequency data; correcting the pulse sequence using the determined transformation to obtain a corrected pulse sequence; and obtaining additional spatial frequency data in accordance with the corrected pulse sequence.

Artefact reduction in magnetic resonance imaging

Systems and methods are provided herein for determining whether to extend scanning performed by a magnetic resonance imaging (MRI) system. According to some embodiments, there is provided a method for imaging a subject using an MRI system, comprising: obtaining data for generating at least one magnetic resonance image of the subject by operating the MRI system in accordance with a first pulse sequence; prior to completing the obtaining the data in accordance with the first pulse sequence, determining to collect additional data to augment and/or replace at least some of the obtained data; determining a second pulse sequence to use for obtaining the additional data; and after completing the obtaining the data in accordance with the first pulse sequence, obtaining the additional data by operating the MRI system in accordance with the second pulse sequence.

Systems and methods for dynamically extending magnetic resonance imaging of a subject

A magnetic resonance (MR) imaging system, comprising a magnetics system having a plurality of magnetics components configured to produce magnetic fields for performing magnetic resonance imaging, and a sensor configured to detect electromagnetic interference conducted by a patient into an imaging region of the MR imaging system. The sensor may comprise at least one electrical conductor configured for electrically coupling to the patient. The MR imaging system may further comprise a noise reduction system configured to receive the electromagnetic interference from the sensor and to suppress electromagnetic interference in detected MR signals received by the MR imaging system based on the electromagnetic interference detected by the sensor.

System and methods for detecting electromagnetic interference in patients during magnetic resonance imaging

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 compensating magnetic resonance imaging (MRI) data for artefacts caused by motion of a subject being imaged. The techniques include obtaining spatial frequency data obtained by using a magnetic resonance imaging (MRI) system to perform MRI on a patient, the spatial frequency data including first spatial frequency data and second spatial frequency data; determining a transformation using a first image obtained using the first spatial frequency data and a second image obtained using the second spatial frequency data; determining a residual spatial phase; correcting, using the transformation, second spatial frequency data and the residual spatial phase, to obtain corrected second spatial frequency data and a corrected residual spatial phase; and generating a magnetic resonance (MR) image using the corrected second spatial frequency data and the corrected residual spatial phase.

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

Systems and methods for generating a gradient waveform for use by a low-field MRI system to generate a gradient magnetic field are provided herein. The gradient waveform can be determined using first information indicative of the gradient waveform and second information indicative of hardware constraints of the low-field MRI system including a maximum voltage of the gradient power amplifier, a maximum slew rate of the gradient coil, a resistance of the gradient coil, and an inductance of the gradient coil. In some embodiments, the gradient waveform can be a trapezoidal gradient waveform determined to have a non-linear ramp-up portion and/or a non-linear ramp-down portion.

Growing community of inventors

Paris, France

Carole Lazarus