General Electric Company

Leland Stanford Junior University

Ge Precision Healthcare LLC

Peng Lai

Joseph Yitan Cheng

Shreyas S Vasanawala

Philip James Beatty

Frank R Korosec

James Hartman Holmes

Weitian Chen

Kang Wang

Christopher Michael Sandino

Anja Christina Sophie Brau

A method of processing signals from an accelerated MRI scan of a dynamic event occurring in the body of a human patient. The patient is subjected to an MRI examination which includes the relevant portion of his body. Those voxels for which there is no substantially no change over the time of the scan are identified and subtracted from the overall scan signal.

Systems and methods for accelerated MRI scan

Various methods and systems are provided for reconstructing magnetic resonance images from accelerated magnetic resonance imaging (MRI) data. In one embodiment, a method for reconstructing a magnetic resonance (MR) image includes: estimating multiple sets of coil sensitivity maps from undersampled k-space data, the undersampled k-space data acquired by a multi-coil radio frequency (RF) receiver array; reconstructing multiple initial images using the undersampled k-space data and the estimated multiple sets of coil sensitivity maps; iteratively reconstructing, with a trained deep neural network, multiple images by using the initial images and the multiple sets of coil sensitivity maps to generate multiple final images, each of the multiple images corresponding to a different set of the multiple sets of sensitivity maps; and combining the multiple final images output from the trained deep neural network to generate the MR image.

Methods and systems for magnetic resonance image reconstruction using an extended sensitivity model and a deep neural network

An MRI system for imaging a moving subject is provided. The MRI system includes a magnet assembly and an MRI controller. The magnet assembly is configured to acquire a k-space via scanning the subject. The acquired k-space includes a plurality of datum each having a motion error. The MRI controller is configured to receive the acquired k-space from the magnet assembly. The MRI controller is further configured to suppress the motion error of each datum by reconstructing the k-space via a soft gating threshold in a non-iterative manner.

System and method for imaging a moving subject

A method for phase-contrast imaging a fluid within a volume of an imaged subject is provided. The method includes acquiring a plurality of slabs, each slab imaging the fluid flowing within a portion of the volume; and volume merging the plurality of slabs to form an image of the volume. Each slab of the plurality is aligned with respect to the volume such that each slab of the plurality is continuously supplied with a plurality of magnetically unsaturated portions of the fluid during acquisition.

System and method for imaging four-dimensional flow of a fluid within a volume of an imaged object

A magnetic resonance imaging data sampling method includes randomly undersampling a first half of a k-space plane such that a plurality of points in the first half are sampled points and the remaining plurality of points in the first half are unsampled points. The method also includes determining, for each sampled point in the first half, a corresponding point in a second half of the k-space plane that corresponds to the point-wise complex conjugate location of the sampled point.

Magnetic resonance imaging data sampling methods and systems

A method for processing magnetic resonance imaging data includes accessing the magnetic resonance imaging data, the data including a plurality of magnetic resonance data sets each collected at different excitation frequencies and defining reconstructable images representative of sections of a single image of a subject. Each magnetic resonance data set includes sampled data for sampled phase encoding points but is missing data for unsampled phase encoding points. The method further includes determining the missing data of at least one of the magnetic resonance data sets using a correlation between the sampled data for the respective magnetic resonance data set and sampled data from at least one other magnetic resonance data set within a spectral window encompassing at least the respective magnetic resonance data set and the at least one other magnetic resonance data set.

Accelerated multispectral data magnetic resonance imaging system and method

In one embodiment, a method for processing magnetic resonance imaging data is provided. The method includes accessing the magnetic resonance imaging data, the data including a plurality of image data sets defining reconstructable images representative of a subject at different points in time. Each data set includes sampled data for sampled phase encoding points but is missing data for unsampled phase encoding points. An adaptive time window is determined for each image data set, and the missing data of at least one of the image data sets is determined based upon the sampled data for the respective data set and sampled data from at least one other data set within the time window for the respective data set.

Growing community of inventors

Menlo Park, CA, United States of America

Peng Lai