Patents by Inventor Shreyas Vasanawala

Shreyas Vasanawala has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20200249300
    Abstract: Various methods and systems are provided for reconstructing magnetic resonance images from accelerated magnetic resonance imaging (MM) data. In one embodiment, a method for reconstructing a magnetic resonance (MR) image includes: estimating multiple sets of coil sensitivity maps from undersampled k-space data, the undersampled k-space data acquired by a multi-coil radio frequency (RF) receiver array; reconstructing multiple initial images using the undersampled k-space data and the estimated multiple sets of coil sensitivity maps; iteratively reconstructing, with a trained deep neural network, multiple images by using the initial images and the multiple sets of coil sensitivity maps to generate multiple final images, each of the multiple images corresponding to a different set of the multiple sets of sensitivity maps; and combining the multiple final images output from the trained deep neural network to generate the MR image.
    Type: Application
    Filed: February 5, 2019
    Publication date: August 6, 2020
    Inventors: Christopher Michael Sandino, Peng Lai, Shreyas Vasanawala, Joseph Yitan Cheng
  • Patent number: 10712416
    Abstract: Various methods and systems are provided for reconstructing magnetic resonance images from accelerated magnetic resonance imaging (MRI) data. In one embodiment, a method for reconstructing a magnetic resonance (MR) image includes: estimating multiple sets of coil sensitivity maps from undersampled k-space data, the undersampled k-space data acquired by a multi-coil radio frequency (RF) receiver array; reconstructing multiple initial images using the undersampled k-space data and the estimated multiple sets of coil sensitivity maps; iteratively reconstructing, with a trained deep neural network, multiple images by using the initial images and the multiple sets of coil sensitivity maps to generate multiple final images, each of the multiple images corresponding to a different set of the multiple sets of sensitivity maps; and combining the multiple final images output from the trained deep neural network to generate the MR image.
    Type: Grant
    Filed: February 5, 2019
    Date of Patent: July 14, 2020
    Assignees: GE PRECISION HEALTHCARE, LLC, THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
    Inventors: Christopher Michael Sandino, Peng Lai, Shreyas Vasanawala, Joseph Yitan Cheng
  • Patent number: 10520573
    Abstract: A method for performing wave-encoded magnetic resonance imaging of an object is provided. The method includes applying one or more wave-encoded magnetic gradients to the object, and acquiring MR signals from the object. The method further includes calibrating a wave point-spread function, and reconstructing an image from the MR signals based at least in part on the calibrated wave point-spread function. Calibration of the wave point-spread function is based at least in part on one or more intermediate images generated from the MR signals.
    Type: Grant
    Filed: April 7, 2017
    Date of Patent: December 31, 2019
    Assignees: GENERAL ELECTRIC COMPANY, THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
    Inventors: Feiyu Chen, Tao Zhang, Joseph Y. Cheng, Valentina Taviani, Brian Hargreaves, John Pauly, Shreyas Vasanawala
  • Publication number: 20180143277
    Abstract: A method for performing wave-encoded magnetic resonance imaging of an object is provided. The method includes applying one or more wave-encoded magnetic gradients to the object, and acquiring MR signals from the object. The method further includes calibrating a wave point-spread function, and reconstructing an image from the MR signals based at least in part on the calibrated wave point-spread function. Calibration of the wave point-spread function is based at least in part on one or more intermediate images generated from the MR signals.
    Type: Application
    Filed: April 7, 2017
    Publication date: May 24, 2018
    Applicants: GENERAL ELECTRIC COMPANY, THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
    Inventors: FEIYU CHEN, TAO ZHANG, JOSEPH Y. CHENG, VALENTINA TAVIANI, BRIAN HARGREAVES, JOHN PAULY, SHREYAS VASANAWALA
  • Patent number: 9726737
    Abstract: In accordance with various embodiments, a radio frequency (RF) coil array for use in a magnetic resonance imaging (MRI) system includes at least first and second RF coils. Each of the RF coils have a main body loop configured to at least one of transmit or receive RF energy at an operating imaging frequency in connection with acquiring MRI image data for an MRI system. The RF coil array also includes first and second cables configured to electrically couple the first and second RF coils, respectively, to a system interface. The RF coil array also includes a common ground connection between the first and second cables. The common ground connection is selectively positioned at a grounding point along lengths of the first and second cables to form a ground loop having a select self-resonance frequency (SRF) that differs from the imaging frequency of the MRI system.
    Type: Grant
    Filed: April 25, 2014
    Date of Patent: August 8, 2017
    Assignee: General Electric Company
    Inventors: Thomas Grafendorfer, Fraser Robb, Greig Scott, Shreyas Vasanawala
  • Publication number: 20140300359
    Abstract: In accordance with various embodiments, a radio frequency (RF) coil array for use in a magnetic resonance imaging (MRI) system includes at least first and second RF coils. Each of the RF coils have a main body loop configured to at least one of transmit or receive RF energy at an operating imaging frequency in connection with acquiring MRI image data for an MRI system. The RF coil array also includes first and second cables configured to electrically couple the first and second RF coils, respectively, to a system interface. The RF coil array also includes a common ground connection between the first and second cables. The common ground connection is selectively positioned at a grounding point along lengths of the first and second cables to form a ground loop having a select self-resonance frequency (SRF) that differs from the imaging frequency of the MRI system.
    Type: Application
    Filed: April 25, 2014
    Publication date: October 9, 2014
    Applicant: General Electric Company
    Inventors: Thomas Grafendorfer, Fraser Robb, Greig Scott, Shreyas Vasanawala
  • Patent number: 8791696
    Abstract: A system and method for generating preamplifier feedback in magnetic resonance imaging (MRI) systems are provided. A preamplifier arrangement for the MRI system includes a plurality of preamplifiers with each of the preamplifiers connected to a different channel of a multi-channel coil array of the MRI system. The preamplifier arrangement further includes a feedback network connected to each of the plurality of preamplifiers with each of the feedback networks configured to generate negative feedback at one or more oscillation frequencies.
    Type: Grant
    Filed: April 9, 2010
    Date of Patent: July 29, 2014
    Assignee: General Electric Company
    Inventors: Thomas Grafendorfer, Paul David Calderon, Fraser Robb, James S. Tropp, Greig Cameron Scott, Shreyas Vasanawala
  • Publication number: 20110248712
    Abstract: A system and method for generating preamplifier feedback in magnetic resonance imaging (MRI) systems are provided. A preamplifier arrangement for the MRI system includes a plurality of preamplifiers with each of the preamplifiers connected to a different channel of a multi-channel coil array of the MRI system. The preamplifier arrangement further includes a feedback network connected to each of the plurality of preamplifiers with each of the feedback networks configured to generate negative feedback at one or more oscillation frequencies.
    Type: Application
    Filed: April 9, 2010
    Publication date: October 13, 2011
    Inventors: Thomas Grafendorfer, Paul David Calderon, Fraser Robb, James S. Tropp, Greig Cameron Scott, Shreyas Vasanawala
  • Patent number: 6922054
    Abstract: Magnetic resonance imaging of a body uses steady state free precession with material separation for the selective imaging of two species, such as blood or fat. The refocusing property of SSFP is used with signal phase detection to suppress either water or lipid. Phase and/or frequency of the RF excitation pulse and repetition time are selected so that resonant frequencies of water, fw, and lipid, fl, are on opposite sides of the signal null frequency.
    Type: Grant
    Filed: August 18, 2003
    Date of Patent: July 26, 2005
    Assignee: The Board of Trustees of The Leland Stanford Junior University
    Inventors: Brian A. Hargreaves, Shreyas Vasanawala
  • Publication number: 20050040821
    Abstract: Magnetic resonance imaging of a body uses steady state free precession with material separation for the selective imaging of two species, such as blood or fat. The refocusing property of SSFP is used with signal phase detection to suppress either water or lipid. Phase and/or frequency of the RF excitation pulse and repetition time are selected so that resonant frequencies of water, fw, and lipid, fl, are on opposite sides of the signal null frequency.
    Type: Application
    Filed: August 18, 2003
    Publication date: February 24, 2005
    Inventors: Brian Hargreaves, Shreyas Vasanawala
  • Patent number: 6452387
    Abstract: A steady-state condition for tipped nuclear spins is accelerated or catalyzed by first determining magnetization magnitude of the steady state and the scaling magnetization along one axis (Mz) to at least approximate the determined magnetization magnitude. Then the scaled magnetization is rotated to coincide with a real-valued eigenvector extension of the tipped steady-state magnetization. Any error vector will then decay to the steady-state condition without oscillation. In one embodiment, the magnetic resonance imaging utilizes steady-state free precession (SSFP). The scaling and rotating steps are followed by the steps of applying read-out magnetic gradients and detecting magnetic resonance signals from the tipped nuclear spins. The magnetization magnitude is determined by eigenvector analysis, and the eigenvector extension is a real-valued eigenvector determined in the analysis.
    Type: Grant
    Filed: March 7, 2001
    Date of Patent: September 17, 2002
    Assignee: Board of Trustees of the Leland Stanford Junior University
    Inventors: Brain A. Hargreaves, Shreyas Vasanawala, John M. Pauly, Dwight G. Nishimura