General Electric Company

Alcatel-lucent USA Inc.

Luca Marinelli

Christopher Judson Hardy

Kevin Franklin King

Ek Tsoon Tan

Marion Irene Menzel

Jonathan Immanuel Sperl

Thomas Kwok-Fah Foo

Kedar Bhalchandra Khare

Dominic Michael Graziani

Lowell Scott Smith

Michael Joseph Flanagan

Sandeep Narendra Gupta

Kai Erik Thomenius

Bruce Allan Hay

Kenneth William Rohling

Ileana Hancu

Robert Marc Lebel

Seung-Kyun Lee

Xiaodong Tao

Eric William Fiveland

Jhimli Mitra

Daniel J Blezek

Zachary Slavens

Daniel Eugene Meyer

Asha Singanamalli

Michael Dominic Graziani

Alvaro H Diaz

Keith J Park

Jayanthi Srinivasan

Kedar Anil Patwardhan

In accordance with the present disclosure, deep-learning techniques are employed to find anomalies corresponding to bleed events. By way of example, a deep convolutional neural network or combination of such networks may be trained to determine the location of a bleed event, such as an internal bleed event, based on ultrasound data acquired at one or more locations on a patient anatomy. Such a technique may be useful in non-clinical settings.

Automated detection and localization of bleeding

Methods and systems using magnetic resonance and ultrasound for tracking anatomical targets for radiation therapy guidance are provided. One system includes a patient transport configured to move a patient between and into a magnetic resonance (MR) system and a radiation therapy (RT) system. An ultrasound transducer is also provided that is hands-free and electronically steerable, securely attached to the patient, such that the ultrasound transducer is configured to acquire four-dimensional (4D) ultrasound images concurrently with one of an MR acquisition or an RT radiation therapy session. The system also includes a controller having a processor configured to use the 4D ultrasound images and MR images from the MR system to control at least one of a photon beam spatial distribution or intensity modulation generated by the RT system. The system determines the previously-acquired correct MR images that represent a specific motion state at some time, t, by a plurality of transformations that allow the representation of the position of fiducial markers in the corresponding ultrasound images to match that of a prior ultrasound acquisition.

Methods and systems to determine respiratory phase and motion state during guided radiation therapy

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

Magnetic material imaging (MMI) system including first and second sets of field-generating coils. Each of the field-generating coils of the first and second sets has an elongated segment that extends along an imaging axis of the medical imaging system. The imaging axis extends through a region-of-interest (ROI) of an object. The elongated segments of the first set of field-generating coils are positioned opposite the elongated segments of the second set of field-generating coils and the ROI is located between the first and second sets of field-generating coils. The MMI system also includes a coil-control module configured to control a flow of current through the first and second sets of field-generating coils to generate a selection field and to generate a drive field. The selection and drive fields combine to form a movable 1D field free region (FFR) that extends through the ROI.

Systems and methods for magnetic material imaging

Systems and methods for generating a magnetic resonance (MR) image of a tissue are provided. A method includes acquiring MR raw data. The MR raw data corresponds to MR signals obtained at undersampled q-space locations for a plurality of q-space locations that is less than an entirety of the q-space locations and the MR signals at the q-space locations represent the three dimensional displacement distribution of the spins in the imaging voxel. The method also includes performing a joint image reconstruction technique on the MR raw data to exploit structural correlations in the MR signals to obtain a series of accelerated MR images and performing, for each image pixel in each accelerated MR image of the series of accelerated MR images, a compressed sensing reconstruction technique to exploit q-space signal sparsity to identify a plurality of diffusion maps.

Diffusion spectrum imaging systems and methods

A method for measuring diffusional anisotropy in diffusion-weighted magnetic resonance imaging. The method includes determining an orientation diffusion function (ODF) for one or more fibers within a single voxel, wherein the ODF includes lobes representative of a probability of diffusion in a given direction for the one or more fibers. The method also includes characterizing an aspect ratio of the lobes. The method further includes determining a multi-directional anisotropy metric for the one or more fibers based on the aspect ratio of the lobes.

Measuring diffusional anisotropy of ODF lobes having maxima peaks and minima troughs with diffusion weighted MRI

Magnetic material imaging (MMI) system including a first array of elongated wire segments that extend substantially parallel to an imaging plane. The imaging plane is configured to extend through a region-of-interest (ROI) of an object. The MMI system also includes a second array of elongated wire segments that extend substantially parallel to the imaging plane. The first and second arrays of wire segments are spaced apart with the imaging plane therebetween. The first and second arrays of wire segments form segment pairs. Each segment pair includes a wire segment of the first array and a wire segment of the second array, wherein the wire segments substantially coincide along a segment plane. The MMI system also includes a phase-control module configured to control a flow of current through the wire segments of the segment pairs to generate and move a one-dimensional field free region (1D FFR) within the imaging plane.

A method of compressed sensing for multi-shell magnetic resonance imaging includes obtaining magnetic resonance imaging data, the data being sampled along multi-shell spherical coordinates, the spherical coordinates coincident with a plurality of spokes that converge at an origin, constructing a symmetric shell for each respective sampled multi-shell to create a combined set of data, performing a three-dimensional Fourier transform on the combined set of data to reconstruct an image, and de-noising the reconstructed image by iteratively applying a sparsifying transform on non-sampled data points of neighboring shells. The method can also include randomly under-sampling the imaging data to create missing data points. A system configured to implement the method and a non-transitory computer readable medium are also disclosed.

Systems and methods for compressed sensing for multi-shell magnetic resonance imaging

The present disclosure relates to a receive coil assembly for use in magnetic resonance imaging of breast tissue. In certain embodiments the assembly comprises separable parts: a configurable mechanical support and a flexible receive coil array. The adjustability and separability of the receive coil array relative to the mechanical support allows the receive coil array to substantially conform to the breasts of the patient during imaging.

Breast coil for use in magnetic resonance imaging

A method of generating a magnetic resonance (MR) image of a tissue includes acquiring MR signals at undersampled q-space encoding locations for a plurality of q-space locations that is less than an entirety of the q-space locations sampled at the Nyquist rate, wherein the acquired signal at the q-space locations represents the three-dimensional displacement distribution of the spins in the imaging voxel, synthesizing the MR signal for the entirety of q-space encodings using a compressed sensing technique for a portion of q-space locations at which MR data was not acquired, combining the acquired MR signals at q-space encodings and the synthesized MR signals at q-space encodings to generate a set of MR signals at q-space encodings that are evenly distributed in q-space, using the set of MR signals at q-space encodings to generate a function that represents a displacement probability distribution function of the set of spins in the imaging voxel, and generating an image of the tissue based on at least a portion of the generated function. A system and computer readable medium are also described herein.

Method and apparatus for performing diffusion spectrum imaging

A magnetic resonance (MR) imaging method includes acquiring MR signals having phase and magnitude at q-space locations using a diffusion sensitizing pulse sequence performed on a tissue of interest, wherein the acquired signals each include a set of complex Fourier encodings representing a three-dimensional displacement distribution of the spins in a q-space location. The signals each include information relating to coherent motion and incoherent motion in the q-space location. The method also includes determining a contribution by coherent motion to the phase of the acquired MR signals; removing the phase contribution attributable to coherent motion from the acquired MR signals to produce a complex data set for each q-space location and an image of velocity components for each q-space location; and producing a three-dimensional velocity image from the image of the velocity components.

Complex reconstruction of Q-space for simultaneous detection of coherent and incoherent motion

A signal processing method is provided. The signal processing method includes the steps of generating undersampled data corresponding to an object, determining a variable thresholding parameter based on a composition of the undersampled data, and iteratively determining thresholded coefficients to generate a plurality of coefficients by utilizing the undersampled data, a current solution and the variable thresholding parameter by updating the variable thresholding parameter and the current solution, and reconstructing a data signal using the plurality of coefficients.

System and method for processing data signals

A signal processing method is presented. The method includes acquiring undersampled data corresponding to an object, initializing a first image solution and a second image solution, determining a linear combination solution based upon the first image solution and the second image solution, generating a plurality of selected coefficients by iteratively updating the first image solution, the second image solution and the linear combination solution and adaptively thresholding one or more transform coefficients utilizing the undersampled data, an updated first image solution, an updated second image solution and an updated linear combination solution, and reconstructing a data signal using the plurality of selected coefficients.

A signal processing method include steps initializing a residual data signal representative of an acquired data signal, determining a significant coefficient corresponding to the residual data signal, updating the residual data signal using the significant coefficient to generate updated residual data signal, iteratively determining significant coefficients to generate a plurality of significant coefficients using the updated residual data signal, updating the plurality of significant coefficients by using a successive approximation technique, to improve the numerical accuracy of the significant coefficients and reconstructing a data signal using the updated plurality of significant coefficients.

Growing community of inventors

Schenectady, NY, United States of America

Luca Marinelli