General Electric Company

Ge Precision Healthcare LLC

Leland Stanford Junior University

Suchandrima Banerjee

John Mark Pauly

Enhao Gong

Greg Zaharchuk

Tim Sprenger

Shreyas S Vasanawala

Brian A Hargreaves

Philip James Beatty

Ajit Shankaranarayanan

Gaohong G Wu

Bruce L Daniel

Valentina Taviani

Arnaud Guidon

Eric Tzguang Han

Baolian Yang

Douglas Link

Emine Ulku Saritas

Jaemin Shin

Systems and methods are provided for a slice-ahead inversion sequence for jointly acquiring non-inverted and inverted contrast. In one example, a method for a magnetic resonance imaging (MRI) system includes acquiring k-space data with the MRI system according to a slice-ahead inversion sequence that jointly generates a contrast without inversion preparation and one or more inversion contrasts for a plurality of slices in a scan volume of a subject, wherein the k-space data comprises first k-space data of the contrast without inversion preparation acquired during one or more non-inversion repetitions and second k-space data of the one or more inversion contrasts acquired during one or more inversion repetitions, wherein a repetition time for each of the one or more non-inversion repetitions and one or more inversion repetitions is constant, and reconstructing one or more images from the k-space data.

Systems and methods for slice-ahead inversion for magnetic resonance imaging

A computer-implemented method and system for performing magnetic resonance diffusion weighted imaging of an object includes generating, via a processor, a diffusion weighted imaging sequence where all diffusion gradients are allocated into N groups such that all imaging slices are acquired for all the diffusion gradients corresponding to a group of the N groups back-to-back in A*TR, wherein N is two or larger, wherein Ais a number of diffusion gradients of each group of the N groups and TR is repetition time, and wherein in each TR every diffusion gradient of the group of the N groups is applied at least once. The computer-implemented method and system also includes acquiring, via the processor, imaging slices for multiple groups of the N groups utilizing the diffusion weighted imaging sequence during a scan of the object utilizing a magnetic resonance imaging scanner.

System and method for diffusion group cycling

Methods and systems for synthesizing contrast images from a quantitative acquisition are disclosed. An exemplary method includes performing a quantification scan, using a trained deep neural network to synthesize a contrast image from the quantification scan, and outputting the contrast image synthesized by the trained deep neural network. In another exemplary method, an operator can identify a target contrast type for the synthesized contrast image. A trained discriminator and classifier module determines whether the synthesized contrast image is of realistic image quality and whether the synthesized contrast image matches the target contrast type.

System and method for synthesizing magnetic resonance images

A system for magnetic resonance imaging an object via a stochastic optimization of a sampling function is provided. The system includes a magnet assembly and a controller. The magnet assembly is operative to acquire MR data from the object. The controller is operative to: acquire a first MR data set using the magnet assembly; select the sampling function from a plurality of sampling function candidates based at least in part on the stochastic optimization; and acquire a second MR data set from the object using the magnet assembly based at least in part on the sampling function.

System and method for magnetic resonance imaging an object via a stochastic optimization of a sampling function

A method for magnetic resonance imaging is provided that includes using a magnetic resonance imaging system to excite a field of view (FOV) for a target being imaged, using an excitation plan to limit the excited FOV to a relatively narrow band of magnetization, exciting multiple bands of magnetization simultaneously, applying phase encoding along a shortest FOV dimension, acquiring a signal from said simultaneously excited bands of magnetization, and reconstructing and outputting a target image from the acquired signal.

High resolution magnetic resonance imaging with reduced distortion based on reduced-field-of-view and generalized parallel imaging

A method for reduced field of view magnetic resonance (MR) imaging includes applying a pulse sequence using a plurality of gradient coils and at least one RF coil of a magnetic resonance imaging system. The pulse sequence includes a two dimensional (2D) echo-planar RF excitation pulse with a plurality of side lobes along a slice select axis and a multiband RF refocusing pulse. MR data is acquired in response to the application of the pulse sequence and at least one MR image is reconstructed based on the MR data. The at least one MR image may then be displayed.

System and method for reduced field of view magnetic resonance imaging

A method for generating a magnetic resonance (MR) image includes acquiring MR data from each of a plurality of RF coils and applying a prospective motion correction method to the MR data for each RF coil including determining a set of motion measurements that include a scan plane orientation associated with each data point in the MR data. The MR data for each RF coil is divided into a plurality of scan plane orientation groups based on motion changes. A set of unaliasing coefficients is generated for each scan plan orientation group and applied to the MR data to synthesize data for each RF coil. The acquired MR data and synthesized data for each RF coil is combined to generate a scan plane orientation data set. Each scan plane orientation data set is combined to generate a complete k-space data set.

System and method for generating a magnetic resonance image using prospective motion correction and parallel imaging

Growing community of inventors

Berkeley, CA, United States of America

Suchandrima Banerjee