Mayo Foundation for Medical Education and Research

Matthew C Murphy

Richard L Ehman

Armando Manduca

Joshua D Trzasko

John Huston, Iii

Jonathan M Scott

Joel P Felmlee

Kevin J Glaser

Arvin Forghanian-Arani

Iii John Huston

John Huston Iii

In accordance with some embodiments, systems, methods, and media for estimating a mechanical property based on a transformation of magnetic resonance elastography (MRE) data using a trained artificial neural network are provided. In some embodiments, a system is provided, the system comprising: a hardware processor programmed to: receive displacement data of tissue in vivo; provide the displacement data to a trained ANN that was trained using noisy input datasets as training data, and derivative datasets corresponding to the noisy input datasets to evaluate performance during training, such that the trained ANN provides an output dataset corresponding to an analytical solution to a derivative of a function represented in an unlabeled input dataset thereby transforming the unlabeled input dataset into its derivative; receive, from the trained ANN, an output dataset indicative of a derivative of the displacement data; and estimate stiffness of the tissue based on the derivative.

Systems, methods, and media for estimating a mechanical property based on a transformation of magnetic resonance elastography data using a trained artificial neural network

Magnetic resonance elastography ('MRE'), or other imaging-based elastography techniques, generate estimates of the mechanical properties, such as stiffness and damping ratio, of tissues in a subject. A machine learning approach, such as an artificial neural network, is implemented to perform an inversion of displacement data in order to generate the estimates of the mechanical properties.

Methods for estimating mechanical properties from magnetic resonance elastography data using artificial neural networks

A system and method for generating a magnetic resonance elastography (MRE) report includes a) acquiring MRE data from a subject including positively motion encoded medical imaging data and negatively motion encoded medical imaging data and b) deriving uncorrected difference medical imaging data from the MRE data for a given slice. The method also includes c) filtering the uncorrected difference medical imaging data to create filtered medical imaging data corrected for errors associated with phase ramps occurring during gradient switching used to derive the positively motion encoded medical imaging data and negatively motion encoded medical imaging data, d) generating a corrected difference image for the given slice from the filtered medical imaging data and the uncorrected difference medical imaging data, e) repeating steps b) through d) for each slice reflected in the MRE data, and f) generating a report of elastic properties of the subject from the corrected difference image.

System and method for improved efficiency in magnetic resonance elastography

Growing community of inventors

Rochester, MN, United States of America

Matthew C Murphy