Leland Stanford Junior University

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

Daniel B Ennis

Shreyas S Vasanawala

Julio A Oscanoa Aida

Matthew J Middione

Michael Loecher

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.

Growing community of inventors

Palo Alto, CA, United States of America

Daniel B Ennis