University of California

Leland Stanford Junior University

The United States Government As Represented by the Department of Veterans Affairs

Daniel Ennis

Eric Aliotta

Shreyas S Vasanawala

Holden H Wu

Julio A Oscanoa Aida

Kevin Moulin

Michael Loecher

Subashini Srinivasan

Matthew J Middione

A method for magnetic resonance imaging (MRI) tag tracking includes: synthetically generating tagged data from natural images combined with programmed tag motion and a full Bloch simulation; training a convolutional neural network (CNN) with the synthetically generated tagged data to generate grid tag motion paths; acquiring MRI images using a tagged imaging method; inputting the acquired images into the CNN to estimate motion paths of tracked points; and determining from the estimated motion paths a path of tag lines through the cardiac cycle from a set of tagged MRI images. The method can calculate strain curves from the estimated motion paths using Ederivation.

Synthetically trained neural network for MRI tag tracking

A method for phase-contrast magnetic resonance imaging (PC-MRI) acquires undersampled PC-MRI data using a magnetic resonance imaging scanner and reconstructs MRI images from the undersampled PC-MRI data by reconstructing a first flow-encoded image using a first convolutional neural network, reconstructing a complex difference image using a second convolutional neural network, combining the complex difference image and the first flow-encoded image to obtain a second flow-encoded image, and generating a velocity encoded image from the first flow-encoded image and second flow-encoded image using phase difference processing.

Artificial intelligence based reconstruction for phase contrast magnetic resonance imaging

A system and method for optimized diffusion-weighted imaging is provided. In one aspect, the method includes providing a plurality of constraints comprising an eddy current constraint for imaging a target at a selected diffusion weighting, and applying an optimization framework to generate an optimized diffusion encoding gradient waveform satisfying the plurality of constraints. The method also includes performing, using the MRI system, a pulse sequence comprising the optimized diffusion encoding gradient waveform to generate diffusion-weighted data, and generating at least one image of the target using the diffusion-weighted data.

System and method for improved diffusion-weighted imaging

A system and method for optimized diffusion-weighted imaging is provided. In one aspect, the method includes providing a plurality of constraints for imaging a target at a selected diffusion weighting, and applying an optimization framework to generate an optimized diffusion encoding gradient waveform satisfying the plurality of constraints. The method also includes performing, using the MRI system, a pulse sequence comprising the optimized diffusion encoding gradient waveform to generate diffusion-weighted data, and generating at least one image of the target using the diffusion-weighted data.

System and method for optimized diffusion-weighted imaging

The present invention provides methods for reducing SAR during real-time MR imaging. The method improves the safety of cine imaging, while, in certain embodiments, do not decrease image quality. The method of the invention thereby allows for the use of higher field strengths that are sometimes necessary to provide the most diagnostic information. The present invention also provides methods for improving contrast-to-noise ratio, while not increasing SAR.

Growing community of inventors

Manhattan Beach, CA, United States of America

Daniel Ennis