Leland Stanford Junior University

General Electric Company

University of California

Ge Precision Healthcare LLC

Joseph Yitan Cheng

Shreyas S Vasanawala

John Mark Pauly

Tao Zhang

Michael Lustig

Christopher Michael Sandino

Feiyu Chen

Peng Lai

David Y Zeng

Brian A Hargreaves

Dwight G Nishimura

Marcus Tedrow Alley

Valentina Taviani

Morteza Mardani Korani

Yuxin Chen

Jiacheng Jason He

A method for magnetic resonance imaging corrects non-stationary off-resonance image artifacts. A magnetic resonance imaging (MRI) apparatus performs an imaging acquisition using non-Cartesian trajectories and processes the imaging acquisitions to produce a final image. The processing includes reconstructing a complex-valued image and using a convolutional neural network (CNN) to correct for non-stationary off-resonance artifacts in the image. The CNN is preferably a residual network with multiple residual layers.

Deep learning method for nonstationary image artifact correction

A method is disclosed for phase contrast magnetic resonance imaging (MRI) comprising: acquiring phase contrast 3D spatiotemporal MRI image data; inputing the 3D spatiotemporal MRI image data to a three-dimensional spatiotemporal convolutional neural network to produce a phase unwrapping estimate; generating from the phase unwrapping estimate an integer number of wraps per pixel; and combining the integer number of wraps per pixel with the phase contrast 3D spatiotemporal MRI image data to produce final output.

Method for correction of phase-contrast magnetic resonance imaging data using a neural network

A method for magnetic resonance imaging (MRI) includes steps of acquiring by an MRI scanner undersampled magnetic-field-gradient-encoded k-space data; performing a self-calibration of a magnetic-field-gradient-encoding point-spread function using a first neural network to estimate systematic waveform errors from the k-space data, and computing the magnetic-field-gradient-encoding point-spread function from the systematic waveform errors; reconstructing an image using a second neural network from the magnetic-field-gradient-encoding point-spread function and the k-space data.

Method for estimating systematic imperfections in medical imaging systems with deep learning

A magnetic resonance imaging scan performs an MRI acquisition using an undersampling pattern to produce undersampled k-space data; adds the undersampled k-space data to aggregate undersampled k-space data for the scan; reconstructs an image from the aggregate undersampled k-space data; updates the undersampling pattern from the reconstructed image and aggregate undersampled k-space data using a deep reinforcement learning technique defined by an environment, reward, and agent, where the environment comprises an MRI reconstruction technique, where the reward comprises an image quality metric, and where the agent comprises a deep convolutional neural network and fully connected layers; and repeats these steps to produce a final reconstructed MRI image for the scan.

Reinforcement learning for online sampling trajectory optimization for magnetic resonance imaging

A method for providing magnetic resonance imaging with dynamic contrast and 4D flow of a volume of an object in a magnetic resonance imaging (MRI) system is provided. Contrast agent is provided to the volume of the object. Magnetic resonance excitation from the MRI system is applied to the volume of the object. The MRI system reads out a subsample of less than 10% of spatially resolved data and velocity encoded data with respect to time. The readout subsample is used to determine both dynamic contrast and 4D flow.

Dynamic contrast enhanced magnetic resonance imaging with flow encoding

A method for magnetic resonance imaging performs unsupervised training of a deep neural network of an MRI apparatus using a training set of under-sampled MRI scans, where each scan comprises slices of under-sampled, unclassified k-space MRI measurements. The MRI apparatus performs an under-sampled scan to produce under-sampled k-space data, updates the deep neural network with the under-sampled scan, and processes the under-sampled k-space data by the updated deep neural network of the MRI apparatus to reconstruct a final MRI image.

Method for performing magnetic resonance imaging reconstruction with unsupervised deep learning

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

A method for magnetic resonance imaging acquires multi-channel subsampled k-space data using multiple receiver coils; performs singular-value-decomposition on the multi-channel subsampled k-space data to produce compressed multi-channel k-space data which normalizes the multi-channel subsampled k-space data; applies a first center block of the compressed multi-channel k-space data as input to a first convolutional neural network to produce a first estimated k-space center block that includes estimates of k-space data missing from the first center block; generates an n-th estimated k-space block by repeatedly applying an (n&#x2212;1)-th estimated k-space center block combined with an n-th center block of the compressed multi-channel k-space data as input to an n-th convolutional neural network to produce an n-th estimated k-space center block that includes estimates of k-space data missing from the n-th center block; reconstructs image-space data from the n-th estimated k-space block.

Generalized multi-channel MRI reconstruction using deep neural networks

An MRI apparatus performs multi-channel calibration acquisitions using a multi-channel receiver array and uses a convolutional neural network (CNN) to compute an estimated profile map that characterizes properties of the multi-channel receiver array. The profile map is composed of orthogonal vectors and transforms single-channel image space data to multi-channel image space data. The MRI apparatus performs a prospectively subsampled imaging acquisition and processes the resulting k-space data using the estimated profile map to reconstruct a final image. The CNN may be pretrained in an unsupervised manner using subsampled simulated multi-channel calibration acquisitions and using a regularization function included in a training loss function.

Unsupervised deep learning for multi-channel MRI model estimation

A method for performing wave-encoded magnetic resonance imaging of an object is provided. The method includes applying one or more wave-encoded magnetic gradients to the object, and acquiring MR signals from the object. The method further includes calibrating a wave point-spread function, and reconstructing an image from the MR signals based at least in part on the calibrated wave point-spread function. Calibration of the wave point-spread function is based at least in part on one or more intermediate images generated from the MR signals.

System and method for performing wave-encoded magnetic resonance imaging of an object

A method for magnetic resonance imaging (MRI) scans a field of view and acquires sub-sampled multi-channel k-space data U. An imaging model A is estimated. Sub-sampled multi-channel k-space data U is divided into sub-sampled k-space patches, each of which is processed using a deep convolutional neural network (ConvNet) to produce corresponding fully-sampled k-space patches, which are assembled to form fully-sampled k-space data V, which is transformed to image space using the imaging model adjoint Ato produce an image domain MRI image. The processing of each k-space patch upreferably includes applying the k-space patch uas input to the ConvNet to infer an image space bandpass-filtered image y, where the ConvNet comprises repeated de-noising blocks and data-consistency blocks; and estimating the fully-sampled k-space patch vfrom the image space bandpass-filtered image yusing the imaging model A and a mask matrix.

Highly-scalable image reconstruction using deep convolutional neural networks with bandpass filtering

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 method for an object in a magnetic resonance image (MRI) system for providing at least one velocity indicative magnetic resonance image (MRI) with motion correction of the object is provided. Velocity encoding gradients in at least one spatial direction are provided from the MRI system. Spatial frequency data resulting from the encoding gradients are acquired through the MRI system. Image signals are provided by the MRI system. Image data resulting from the image signals are acquired through the MRI system. At least one motion corrected and velocity indicative magnetic resonance image is created from the acquired spatial frequency data and image data.

Intrinsic navigation from velocity-encoding gradients in phase-contrast MRI

A method for providing at least one motion corrected magnetic resonance imaging (MRI) image of an object in an MRI system with an array of a plurality of receiving coils is provided. At least one motion navigator signal of the object is provided. Individual navigator data are collected from each of the plurality of receiving coils. Motion estimates are generated for each of the plurality of receiving coils from the collected individual navigator data. A subset of the plurality of coils is found that detects a dominant motion by clustering the generated motion estimates. Only motion estimates from coils in the found subset are used to create a determined motion estimate. At least one MRI image is reconstructed using the determined motion estimate.

Robust self-navigating MRI using large coil arrays

A method for providing an magnetic resonance imaging (MRI) with nonrigid motion correction of an object is provided. An MRI excitation is applied to the object. A magnetic field read out from the object using a plurality of sensor coils. Spatially localized motion estimates are obtained for each sensor coil of the plurality of sensor coils. The motion estimates are used for each sensor coil to provide motion correction.

Growing community of inventors

Los Altos, CA, United States of America

Joseph Yitan Cheng