General Electric Company

Ge Precision Healthcare LLC

King's College London

Florian Wiesinger

Dattesh Dayanand Shanbhag

Sandeep Suryanarayana Kaushik

Ana Beatriz Solana Sanchez

Christopher Judson Hardy

Rakesh Mullick

Sheshadri Thiruvenkadam

Laura Irene Sacolick

Anne Menini

Thomas Kwok-Fah Foo

Ravindra Mohan Manjeshwar

Selaka Bandara Bulumulla

Ileana Hancu

Sangtae Ahn

Hua Qian

Robert David Darrow

Charles William Stearns

Thomas K F Foo

Kevin Matthew Koch

Dawei Gui

Robert Marc Lebel

Tao Tan

Xiaoli Zhao

Desmond Teck Beng Yeo

Chitresh Bhushan

Floribertus Philippus Heukensfeldt Jansen

Timothy Wayne Deller

Anja C S Brau

Lehel Ferenczi

Sudhanya Chatterjee

László Ruskó

Hua Li

Dirk Bequé

Peder E Larson

Sagar Mandava

Dirk Lange

Kang Wang

Ty A Cashen

Matthew Richard Tarasek

Balázs Péter Cziria

Martin Andreas Janich

Harsh Kumar Agarwal

Kavitha Manickam

Mika Vogel

Gareth John Barker

Hongxiang Yi

Richárd Zsámboki

Kristen Ann Wangerin

Silke Maria Lechner-Greite

Cristina Cozzini

Michael Carl

Rolf Schulte

Seung Kyun Lee

Thomas Kwok-Foo

Emil Albert Ljungberg

Mathias Engstrom

Mika W Vogel

Tobias Charles Wood

Brice Fernandez

Andrew Leynes

Steven Charles Williams

Lishui Cheng

Vanda Czipczer

Nicolas Hehn

Bernadett Kolozsvári

Fei Mian

Attila Márk Rádics

Zhenghui Zhang

A computer-implemented method for generating a chemical shift artifact corrected reconstructed image from magnetic resonance imaging (MRI) data includes inputting into a trained deep neural network an image generated from the MRI data acquired during a non-Cartesian MRI scan of a subject. The method also includes utilizing the trained deep neural network to generate the chemical shift artifact corrected reconstructed image from the image, wherein the trained deep neural network was trained utilizing a tissue mixing model that models interactions between different tissue types to mitigate chemical shift artifacts. The method further includes outputting from the trained deep neural network the chemical shift artifact corrected reconstructed image.

System and method for deep learning-based chemical shift artifact mitigation of non-Cartesian magnetic resonance imaging data

A method for performing a scan of a subject utilizing a magnetic resonance imaging (MRI) system includes triggering a prescan by an MRI scanner of the MRI system upon the subject being setup on a table of the MRI scanner and the table reaching an iso-center of the MRI scanner. The method includes subsequent to the prescan, triggering a calibration scan of the subject with the MRI scanner, wherein the calibration scan is an acoustic noise suppressed MRI scan. The method includes obtaining calibration data from the calibration scan. The method includes obtaining prescription parameters for subsequent scans of the subject with the MRI scanner from the calibration data. The method includes triggering at least one scan of the subject with the MRI scanner based on the prescription parameters.

System and method for improving magnetic resonance scanning workflow

Methods and systems are provided for segmenting structures in medical images. In one embodiment, a method includes receiving an input dataset including a set of medical images, a structure list specifying a set of structures to be segmented, and a segmentation protocol, performing an input check on the input dataset, determining whether each medical image of the set of medical images has passed the input check and removing any medical images from the set of medical images that do not pass the input check to form a final set of medical images, segmenting each structure from the structure list using one or more segmentation models and the final set of medical images, receiving a set of segmentations output from the one or more segmentation models, processing the set of segmentations to generate a final set of segmentations, and displaying and/or saving in memory the final set of segmentations.

Systems and methods for segmenting objects in medical images

A method for generating an image of an object with a magnetic resonance imaging (MM) system is presented. The method includes first performing a calibration scan of the object. The calibration scan is performed with a zero echo time (ZTE) radial sampling scheme to obtain calibration k-spaces for surface coil elements and a body coil of the MRI system. The calibration scan is performed in such a manner that the endpoints of calibration k-space lines in each calibration k-space follow a spiral path. A plurality of calibration parameters are then obtained from the plurality of calibration k-spaces. A second scan of the object is then performed to acquire the MR image data. The image of the object is then generated based on the plurality of calibration parameters and the MR image data.

Silent calibration for magnetic resonance imaging

Various methods and systems are provided for translating magnetic resonance (MR) images to pseudo computed tomography (CT) images. In one embodiment, a method comprises acquiring an MR image, generating, with a multi-task neural network, a pseudo CT image corresponding to the MR image, and outputting the MR image and the pseudo CT image. In this way, the benefits of CT imaging with respect to accurate density information, especially in sparse regions of bone which exhibit with high dynamic range, may be obtained in an MR-only workflow, thereby achieving the benefits of enhanced soft-tissue contrast in MR images while eliminating CT dose exposure for a patient.

Methods and systems for translating magnetic resonance images to pseudo computed tomography images

A method of controlling and processing data from a hybrid PET-MR imaging system includes acquiring a positron emission tomographic (PET) dataset over a time period, wherein the PET dataset is affected by a quasi-periodic motion of the patient, and acquiring magnetic resonance (MR) data during the time period such that the acquisition time of the MR data relative to the PET dataset is known. A characteristic of the patient motion is then determined based on the PET dataset and the MR data is processed based on the characteristic of patient motion.

Method and system for motion compensation in hybrid PET-MR imaging

A magnetic resonance (MR) dynamically imaging method is provided. The method includes acquiring a functional MR dataset including frames of k-space datasets, while a functional stimulus is applied to the subject. Acquiring the functional MR dataset includes, acquiring a frame of k-space datasets by setting an orientation as an initial angle, and acquiring a free induction decay (FID) dataset. Acquiring an FID dataset includes applying a sequence of gradients, each gradient of the sequence corresponding to a k-space spoke, wherein the sequence of k-space spokes define a k-space segment having the orientation in a 3D k-space volume. Acquiring a frame of k-space datasets also includes acquiring a gradient echo dataset corresponding to the FID dataset, and updating the orientation as golden angles. The method also includes generating anatomical MR images and functional images based on the functional MR dataset.

Systems and methods of silent multi-gradient echo dynamic magnetic resonance imaging

A method for generating motion-corrected medical images includes obtaining, via a processor, k-space data of a region of interest acquired by a magnetic resonance imaging system utilizing a 3D radial pulse sequence with ZTE acquisition including optional magnetization preparation pulses. The method also includes sampling, via the processor, the k-space data to obtain a plurality of interleaved k-space segments. The method further includes reconstructing, via the processor, one or more interleaved k-space segments of the plurality of interleaved k-space segments to generate a respective motion navigator volume. The method even further includes co-registering, via the processor, each respective motion navigator volume to estimate motion and performing motion correction on the one or more interleaved k-space segments and their corresponding k-space trajectories. The method still further includes generating, via the processor, a motion-corrected volume from all of the motion corrected interleaved k-space segments and their corresponding motion corrected k-space trajectories.

System and method for performing motion-insensitive and quiet three-dimensional magnetic resonance imaging

Systems and methods for ZTE MRI are disclosed. An exemplary method includes obtaining Larmor frequencies of water and/or fat for a region of interest of a subject to be imaged at a pre-scan and setting a center frequency for an RF transceiver of the MR system at a value between the Larmor frequencies of water and fat. A ZTE pulse sequence is applied to the subject and MR signals in response to the ZTE pulse sequence are received from the subject. The received MR signals are demodulated with the center frequency and an in-phase ZTE image is generated from the demodulated MR signals.

Systems and methods for in-phase zero echo time magnetic resonance imaging

An imaging system and method are disclosed. An MR image and measured B0 field map of a target volume in a subject are reconstructed, where the MR image includes one or more bright and/or dark regions. One or more distinctive constituent materials corresponding to the bright regions are identified. Each dark region is iteratively labeled as one or more ambiguous constituent materials. Susceptibility values corresponding to each distinctive and iteratively labeled ambiguous constituent material is assigned. A simulated B0 field map is iteratively generated based on the assigned susceptibility values. A similarity metric is determined between the measured and simulated B0 field maps. Constituent materials are identified in the dark regions based on the similarity metric to ascertain corresponding susceptibility values. The MRI data is corrected based on the assigned and ascertained susceptibility values. A diagnostic assessment of the target volume is determined based on the corrected MRI data.

Method and system for improved classification of constituent materials

Methods and systems to obtain and apply Tpreparatory radiofrequency (RF) pulse sequences for magnetic resonance imaging (MRI) are provided. The iterative methods may employ propagation of the magnetization state of the object being imaged and a comparison with a target magnetization state. The methods disclosed may be used to obtain MRI pulse sequences that may optimize Trelaxation contrast. The produced RF pulse sequences may be robust to effects from inhomogeneity of the magnetic fields or other environmental or physiological perturbations.

Magnetic resonance T2 preparatory pulses for magnetic field inhomogeneity robustness and contrast optimization

Methods and systems for production of silent, multi-gradient-echo, magnetic resonance images are provided. The methods employ iterative application of small updates to the magnetic field gradient followed by a short, non-selective radiofrequency pulse excitation and for free induction decay data acquisition. The magnetic field gradient updates allow for silent, self-refocusing pulse sequence. Subsequent applications of the magnetic field gradients allow for multiple echo data acquisitions, which may allow fast, silent production of T2*-weighted images.

Silent multi-gradient echo magnetic resonance imaging

A system and method for tracking temperature changes in tissue and bone is disclosed. In one aspect, the temperature changes are tracked simultaneously with high spatial encoding and temporal efficiency. The method is robust in terms of B0 and chemical shift off-resonance, as well as insensitive to eddy currents for accurate temperature mapping. Zero TE (ZTE) based MR thermometry is utilized herein to extract temperature changes from proton density and T1 weighted images. Additionally, T1 signal contamination is corrected for by calibrating T1 and B0 by using a variable flip angle method to achieve temperature mapping in bone, aqueous and adipose tissue simultaneously.

Proton density and T1 weighted zero TE MR thermometry

A system and method for estimating image intensity bias and segmentation tissues is presented. The system and method includes obtaining a first image data set and at least a second image data set, wherein the first and second image data sets are representative of an anatomical region in a subject of interest. Furthermore, the system and method includes generating a baseline bias map by processing the first image data set. The system and method also includes determining a baseline body mask by processing the second image data set. In addition, the system and method includes estimating a bias map corresponding to a sub-region in the anatomical region based on the baseline body mask. Moreover, the system and method includes segmenting one or more tissues in the anatomical region based on the bias map.

System and method for image intensity bias estimation and tissue segmentation

Aspects of the invention relate to generating an emission activity image as well as an emission attenuation map using an iterative updation based on both the raw emission projection data and the raw radiography projection data, and an optimization function. The outputs include an optimized emission activity image, and at least one of an optimized emission attenuation map or an optimized radiography image. In some aspects an attenuated corrected emission activity image is obtained using the optimized emission activity image, and the optimized emission attenuation map.

Systems and methods for reconstruction of emission activity image

Growing community of inventors

Freising, Germany

Florian Wiesinger