Siemens Healthcare Gmbh

The United States of America, As Represented by the Secretary, Department of Health and Human Services

University of Virginia Patent Foundation

Siemens Healthineers Ag

University of Alberta

Kelvin Chow

Dorin Comaniciu

Mariappan S Nadar

Peter Speier

Boris Mailhe

Simon Arberet

Hui Xue

Michael Salerno

Ning Jin

Peter Kellman

Yang Yang

Bruce S Spottiswoode

Laszlo Lazar

Richard Thompson

Nirmal Janardhanan

Michael Bush

For magnetic resonance (MR) reconstruction using artificial intelligence (AI), the AI-based reconstruction for MR imaging systems is offloaded to one or more servers. A remote server performs AI-based reconstruction. A library of recent, old, custom, and/or publicly available AI-based reconstruction processes may be rapidly deployed and available to the server, which has the memory and processing resources for AI-based reconstruction. Load balancing of the data and/or between servers may improve performance.

Architecture for artificial intelligence-based magnetic resonance reconstruction

In a method and magnetic resonance (MR) apparatus for pulse wave velocity (PWV) measurement along the aorta of a subject using MR imaging, a multislice cardio synchronized segmented cin&#xe9; MR data acquisition sequence is optimized in order to enhance inflow representation in the slice images, in order to make the multislice MR data acquisition sequence viable for clinical uses, so as to acquire intensity-based MR data from two transverse slices spaced from each other along the descending aorta. The respective intensities of relevant pixels in at least two respective slice images are analyzed in order to identify the arrival of a pulse wave in the respective slices by the onset of flow enhancement in the slices, represented by intensity changes in the pixels. From the onset of flow enhancement in the respective slice images, PWV is calculated. An electronic signal representing the calculated PWV is then provided from a computer.

Inflow-based pulse wave velocity profiling along the aorta using magnetic resonance imaging

Systems and methods to determine a first map of a first parameter based on first signals acquired by a magnetic resonance imaging system, the first map associating each of a plurality of voxels with a respective value of the first parameter, the first parameter quantifying a first physical characteristic of an object represented by the plurality of voxels, determine a second map of a second parameter based on the first signals, the second map associating each of the plurality of voxels with a respective value of the second parameter, the second parameter quantifying a second physical characteristic of the object, and determine a dark-blood phase-sensitive inversion recovery late gadolinium enhancement image based on the first map of the first parameter and on the second map of the second parameter.

Synthetic bright-blood and dark-blood PSIR LGE images

A method for performing magnetic resonance imaging with variable flip angle (VFA) readouts includes preparing longitudinal magnetization of a spin system associated with a subject to a target state, yielding a prepared longitudinal magnetization. The prepared longitudinal magnetization is converted to an image using a VFA readout sequence, wherein the VFA readout sequence comprises a plurality of radio-frequency pulses with corresponding flip-angles varying according to a modulation function.

Accuracy and off-resonance performance in quantitative magnetization prepared magnetic resonance imaging

In one aspect, the disclosed technology relates to a method which, in one example embodiment, includes acquiring magnetic resonance imaging data for a plurality of images of the heart of a subject during free breathing of the subject. The method also includes generating an additional plurality of images with high tissue-blood contrast over the region of interest, and selecting a subset of images from the plurality of images, based upon a pre-determined quality metric of image similarity, to be used for non-rigid image registration. The method also includes aligning the subset of images by non-rigid image registration using a combination of the plurality of images and the additional plurality of images, and creating a parametric map from the aligned images.

Free-breathing parameter mapping with high-contrast image registration

Growing community of inventors

Chicago, IL, United States of America

Kelvin Chow