General Electric Company

Ge Precision Healthcare LLC

The Johns Hopkins University

Christopher Judson Hardy

Luca Marinelli

Harvey E Cline

Ek Tsoon Tan

Thomas Kwok-Fah Foo

Charles L Dumoulin

Sangtae Ahn

Kevin Franklin King

Robert David Darrow

Selaka Bandara Bulumulla

Kenneth William Rohling

Itzik Malkiel

Paul Arthur Bottomley

Manojkumar Saranathan

Rafael Shmuel Brada

Marion Irene Menzel

Jonathan Immanuel Sperl

Thomas K F Foo

Peter B Roemer

Ron Wein

Florian Wiesinger

Yudong Zhu

William D Barber

Kedar Bhalchandra Khare

Randy Otto John Giaquinto

William Thomas Dixon

Michael Rotman

Ravindra Mohan Manjeshwar

Ronald Dean Watkins

Dattesh Dayanand Shanbhag

William E Lorensen

John F Schenck

Erika Schneider

Charles Lucian Dumoulin

Daniel J Blezek

Isabelle Heukensfeldt Jansen

Sasikanth Manipatruni

Matthew N O'Donnell

William A Edelstein

Stephen J Riederer

Robert Steven Stormont

Charles William Stearns

Rakesh Mullick

Graeme Colin McKinnon

Otward M Mueller

Edward James Nieters

Kathleen Melanie Amm

Shekhar Dwivedi

Robert Marc Lebel

Josef P Debbins

Sheshadri Thiruvenkadam

Prem Venugopal

Vivek Prabhakar Vaidya

Xiaodong Tao

Zachary Slavens

Ray Fli Lee

Dominic Michael Graziani

Kirby Gannett Vosburgh

Albert Henry Roger Lonn

Anja Christina Sophie Brau

Uri Wollner

Sheila Srinivasan Washburn

Graeme C Mckinnon

Stephen Joseph Garnier

Rupert William Curwen

Samuel M Blumenfeld

Richard L St Peters

Umesha Perdoor Srinivas Adiga

Stephen A Ash

Manjeshwar Mohan Ravindra

Steven P Suza

Karthikeyan Veeraswamy Sathyamurthy

Thomas Kwok-Foo

Jason Scott Pelc

Cornelius Jan Von Morze

Giang-Chau Ngo

A computer-implemented method of processing complex magnetic resonance (MR) images is provided. The method includes receiving a pair of corrupted complex data and pristine complex images. The method also includes training a neural network model using the pair by inputting the corrupted complex data to the neural network model, setting the pristine complex images as target outputs, and processing the corrupted complex data using the neural network model to derive output complex images of the corrupted complex data. Training a neural network model also includes comparing the output complex images with the target outputs by computing a phase-sensitive structural similarity index measure (PS-SSIM) between each of the output complex images and its corresponding target complex image, wherein the PS-SSIM is real-valued and varies with phases of the output complex image and phases of the target complex image, and adjusting the neural network model based on the comparison.

Systems and methods of processing magnetic resonance images using phase-sensitive structural similarity index measure

K-space data obtained from a magnetic resonance imaging scan where motion was detected is split into two parts in accordance with the timing of the motion to produce first and second sets of k-space data corresponding to different poses. Sub-images are reconstructed from the k first and second sets of k-space data, which are used as inputs to a deep neural network which transforms them into a motion-corrected image.

System and method for correcting for patient motion during MR scanning

A magnetic resonance (MR) imaging method of detecting and scoring motion artifacts in MR images of an object is provided. The method includes computing a k-space difference map based at least in part on first MR signals of the object acquired with a first coil and second MR signals of the object acquired with a second coil. The method also includes generating a difference plot based on the k-space difference map, the difference plot including a curve. The method further includes calculating a motion score based on the curve in the difference plot, wherein the motion score indicates the level of motion artifacts in the image caused by motion of the object during acquisition of the first MR signals and the second MR signals, and the motion score includes an area under the curve. Moreover, the method includes outputting the motion score.

Systems and methods of automatically detecting and scoring motion artifacts in magnetic resonance imaging

The techniques discussed herein relate to a reduced acoustic noise and vibration magnetic resonance imaging (MRI) acquisition. In certain implementations acoustic noise levels for one or more MRI pulse sequences are characterized and modified by limiting the frequencies and amplitudes of the gradient waveforms so as to produce less noise and vibration when the modified waveform is used during an MRI examination. In this manner, relatively low sound pressure levels can be attained.

Low acoustic noise magnetic resonance image acquisition

The subject matter discussed herein relates to a fast magnetic resonance imaging (MRI) method to suppress fine-line artifact in Fast-Spin-Echo (FSE) images reconstructed with a deep-learning network. The network is trained using fully sampled NEX=2 (Number of Excitations equals to 2) data. In each case, the two excitations are combined to generate fully sampled ground-truth images with no fine-line artifact, which are used for comparison with the network generated image in the loss function. However, only one of the excitations is retrospectively undersampled and inputted into the network during training. In this way, the network learns to remove both undersampling and fine-line artifacts. At inferencing, only NEX=1 undersampled data are acquired and reconstructed.

Reconstruction of MR image data

A method is provided that includes acquiring coil data from a magnetic resonance imaging device. The coil data includes undersampled k-space data. The method includes processing the coil data using an image reconstruction technique to generate an initial undersampled image. The method includes generating a reconstructed image based on the coil data, the initial undersampled image, and multiple iterative blocks of a residual deep-learning image reconstruction network. A first iterative block of the residual deep-learning image reconstruction network receives the initial undersampled image. Each of the multiple iterative blocks includes a data-consistency unit that preserves the fidelity of the coil data in a respective output of a respective iterative block utilizing zeroed data consistency. The initial undersampled image is added to an output of the last iterative block via a residual connection. The residual deep-learning image reconstruction network is a neural network trained using previously acquired coil data.

System and method for sparse image reconstruction utilizing null data consistency

A method of reconstructing imaging data into a reconstructed image may include training a generative adversarial network (GAN) to reconstruct the imaging data. The GAN may include a generator and a discriminator. Training the GAN may include determining a combined loss by adaptively adjusting an adversarial loss based at least in part on a difference between the adversarial loss and a pixel-wise loss. Additionally, the combined loss may be a combination of the adversarial loss and the pixel-wise loss. Training the GAN may also include updating the generator based at least in part on the combined loss. The method may also include receiving, into the generator, the imaging data and reconstructing, via the generator, the imaging data into a reconstructed image.

Method and apparatus for using generative adversarial networks in magnetic resonance image reconstruction

A magnetic resonance imaging (MRI) system includes control and analysis circuitry having programming to acquire magnetic resonance (MR) data using coil elements of the MRI system, analyze the MR data, and reconstruct the MR data into MR sub-images. The system also includes a trained neural network associated with the control and analysis circuitry to transform the MR sub-images into a prediction relating to a presence and extent of motion corruption in the MR sub-images. The programming of the control and analysis circuitry includes instructions to control operations of the MRI system based at least in part on the prediction of the trained neural network.

MRI system and method using neural network for detection of patient motion

A system and method for detecting, timing, and adapting to patient motion during an MR scan includes using the inconsistencies between calculated images from different coil-array elements to detect the presence of patient motion and, together with the k-space scan-order information, determine the timing of the motion during the scan. Once the timing is known, various actions may be taken, including restarting the scan, reacquiring those portions of k-space acquired before the movement, or correcting for the motion using the existing data and reconstructing a motion-corrected image from the data.

MRI system and method for detection and correction of patient motion

A magnetic resonance (MR) imaging method performed by an MR imaging system includes acquiring MR data in multiple shots and multiple acquisitions (NEX), separately reconstructing the component magnitude and phase of images corresponding to the multiple shots and multiple NEX, removing the respective phase from each of the images, and combining, after removal of the respective phase, the shot images and the NEX images to produce a combined image. The method further includes using the combined image to calculate the full k-space data for each shot and NEX and replacing unacquired k-space data points with calculated k-space data points. The operations are repeated until the combined image reaches a convergence.

Method and systems for iteratively reconstructing multi-shot, multi-acquisition MRI data

A method for sparse image reconstruction includes acquiring coil data from a magnetic resonance imaging device. The coil data includes undersampled k-space data corresponding to a subject. The method further includes processing the coil data using an image reconstruction technique to generate an initial undersampled image. The method also includes generating a reconstructed image based on the coil data, the initial undersampled image, and a plurality of iterative blocks of a flared network. A first iterative block of the flared network receives the initial undersampled image. Each of the plurality of iterative blocks includes a data consistency unit and a regularization unit and the iterative blocks are connected both by direct connections from one iterative block to the following iterative block and by a plurality of dense skip connections to non-adjacent iterative blocks. The flared network is based on a neural network trained using previously acquired coil data.

System and method for sparse image reconstruction

A method for determining an arterial pulse wave velocity representative of a health condition of a blood vessel includes receiving an image data set comprising a plurality of images of a subject, from an imaging modality. The method also involves determining a blood vessel region in an image from the plurality of images. The method further includes determining a plurality of cross-sectional area values of a blood vessel at a plurality of locations in the blood vessel region, corresponding to a plurality of phases of a cardiac cycle of the subject and determining a plurality of flow rate values of blood flowing in the blood vessel corresponding to the plurality of cross-sectional area values. The method also includes determining a hemodynamic model based on the plurality of cross-sectional area values and the plurality of blood flow rate values and determining the arterial pulse wave velocity based on the hemodynamic model.

System and method for estimating arterial pulse wave velocity

A magnetic resonance imaging method includes generating spatially resolved fiber orientation distributions (FODs) from magnetic resonance signals acquired from a patient tissue using a plurality of diffusion encodings, each acquired magnetic resonance signal corresponding to one of the diffusion encodings and being representative of a three-dimensional distribution of displacement of magnetic spins of gyromagnetic nuclei present in each imaging voxel. Generating the spatially resolved FODs includes performing generalized spherical deconvolution using the acquired magnetic resonance signals and a modeled tissue response matrix (TRM) to reconstruct the spatially resolved FODs. The method also includes using the spatially resolved FODs to generate a representation of fibrous tissue within the patient tissue.

Generalized spherical deconvolution in diffusion magnetic resonance imaging

Systems and methods for correcting magnetic resonance (MR) data are provided. One method includes receiving the MR data and correcting errors present in the MR data due to non-uniformities in magnetic field gradients used to generate the diffusion weighted MR signals. The method also includes correcting errors present in the MR data due to concomitant gradient fields present in the magnetic field gradients by using one or more gradient terms. At least one of the gradient terms is corrected based on the correction of errors present in the MR data due to the non-uniformities in the magnetic field gradients.

Magnetic resonance imaging data correction methods and systems

A system, non-transitory computer-readable medium, and method of designing quiet variable-rate MRI slice-select pulses includes creating discretized first slice-select constant-amplitude gradient and RF waveforms, associating discretized time points having a first constant time increment with the first waveforms, selecting a scaling function that smooths the gradient waveform when multiplied together, multiplying the gradient and RF waveforms by the corresponding value of the scaling function to create second gradient and RF waveforms, dividing the time increment between the discretized time points by the corresponding value of the scaling function to create a remapped time increment, cumulatively summing the remapped time increments to create a remapped time scale, interpolating the second gradient and RF waveforms along the remapped time scale to form final gradient and RF waveforms, and providing the final gradient and RF waveforms for incorporation into an MRI pulse sequence.

Systems and methods for design of magnetic resonance imaging slice-select pulses

Growing community of inventors

Schenectady, NY, United States of America

Christopher Judson Hardy