Patents by Inventor Andrew G. Jeung

Andrew G. Jeung 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).

  • Patent number: 11669967
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Grant
    Filed: June 10, 2022
    Date of Patent: June 6, 2023
    Assignee: VARIAN MEDICAL SYSTEMS, INC.
    Inventors: Hassan Mostafavi, Alexander Sloutsky, Andrew G. Jeung
  • Publication number: 20220301280
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Application
    Filed: June 10, 2022
    Publication date: September 22, 2022
    Inventors: Hassan MOSTAFAVI, Alexander SLOUTSKY, Andrew G. JEUNG
  • Patent number: 11367275
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Grant
    Filed: May 22, 2020
    Date of Patent: June 21, 2022
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hassan Mostafavi, Alexander Sloutsky, Andrew G. Jeung
  • Publication number: 20200285915
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Application
    Filed: May 22, 2020
    Publication date: September 10, 2020
    Applicant: Varian Medical Systems, Inc.
    Inventors: Hassan MOSTAFAVI, Alexander SLOUTSKY, Andrew G. JEUNG
  • Patent number: 10742956
    Abstract: A system for determining positional information of a camera, includes: a plane determination module configured to determine a first plane and a second plane based on a depth image; a plane-association module configured to associate the first plane determined by the plane determination module with a first tool-plane, and to associate the second plane determined by the plane determination module with a second tool-plane, the first and second tool-planes having known positional relationship with respect to each other; and a positional determination unit configured to determine the positional information of the camera based on an output from the plane-association module.
    Type: Grant
    Filed: August 24, 2016
    Date of Patent: August 11, 2020
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hassan Mostafavi, Andrew G. Jeung, Alexander Sloutsky, David H. Humber
  • Patent number: 10679104
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Grant
    Filed: October 26, 2012
    Date of Patent: June 9, 2020
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hassan Mostafavi, Alexander Sloutsky, Andrew G. Jeung
  • Patent number: 9939130
    Abstract: A marker system includes: a first marker; and a second marker; wherein the first marker and the second marker are configured to emit light from one or more light sources coupled to the first marker and the second marker; and wherein the first marker and the second marker are configured to emit the light for detection by a camera. A method performed using a marker system includes: generating light using one or more light sources; emitting the light at a plurality of markers that are coupled to the light sources; and detecting the light emitted from the plurality of markers using a camera; wherein the act of detecting comprises using one or more filters to reduce ambient light to a level that corresponds with a noise level of the camera while allowing light emitted from the markers to be imaged by the camera.
    Type: Grant
    Filed: September 27, 2013
    Date of Patent: April 10, 2018
    Assignee: Varian Medical Systems, Inc.
    Inventors: Andrew G. Jeung, Hassan Mostafavi, George A. Zdasiuk, Gary F. Virshup, Dusan Baic, Daniel R. Bilsky, Alexander R. Brown, Jon Carver, Graham Faulknor, Alyssa Garver, Arthur Kwun, Michelle Richmond, Josh M. Star-Lack, John G. Van Heteren
  • Publication number: 20180061036
    Abstract: A system for determining positional information of a camera, includes: a plane determination module configured to determine a first plane and a second plane based on a depth image; a plane-association module configured to associate the first plane determined by the plane determination module with a first tool-plane, and to associate the second plane determined by the plane determination module with a second tool-plane, the first and second tool-planes having known positional relationship with respect to each other; and a positional determination unit configured to determine the positional information of the camera based on an output from the plane-association module.
    Type: Application
    Filed: August 24, 2016
    Publication date: March 1, 2018
    Applicant: VARIAN MEDICAL SYSTEMS, INC.
    Inventors: Hassan MOSTAFAVI, Andrew G. JEUNG, Alexander SLOUTSKY, David H. HUMBER
  • Patent number: 9886534
    Abstract: A method of detecting a possible collision in a medical procedure that involves a medical system, includes: obtaining an image of a patient that is supported on a patient support; determining a first model using a processing unit based at least in part on the image, at least a part of the first model representing a surface of the patient; determining a second model using the processing unit, the second model representing a first component of the medical system; virtually moving the first model, the second model, or both, using a collision prediction mechanism to simulate a movement of the first component of the medical system to determine whether there is a possible collision between the first component and the patient; and generating an output to indicate the possible collision or an absence of the possible collision.
    Type: Grant
    Filed: February 3, 2016
    Date of Patent: February 6, 2018
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hong Wan, Raymond Kraft, Sun-Kai Lin, Stephen C. Phillips, Anthony Harrington, Hassan Mostafavi, Alexander Sloutsky, Andrew G. Jeung
  • Publication number: 20170220709
    Abstract: A method of detecting a possible collision in a medical procedure that involves a medical system, includes: obtaining an image of a patient that is supported on a patient support; determining a first model using a processing unit based at least in part on the image, at least a part of the first model representing a surface of the patient; determining a second model using the processing unit, the second model representing a first component of the medical system; virtually moving the first model, the second model, or both, using a collision prediction mechanism to simulate a movement of the first component of the medical system to determine whether there is a possible collision between the first component and the patient; and generating an output to indicate the possible collision or an absence of the possible collision.
    Type: Application
    Filed: February 3, 2016
    Publication date: August 3, 2017
    Applicant: Varian Medical Systems, Inc.
    Inventors: Hong WAN, Raymond KRAFT, Sun-Kai LIN, Stephen C. PHILLIPS, Anthony HARRINGTON, Hassan MOSTAFAVI, Alexander SLOUTSKY, Andrew G. JEUNG
  • Patent number: 9119541
    Abstract: An apparatus for prompting a patient includes a structure configured to be mounted to a patient support, a screen coupled to the structure, and a projector located at a distance away from the screen. A method of prompting a patient that is being supported on a patient support includes adjusting a position of a screen relative to a projector, the screen having a surface, placing the screen in front of the patient such that the patient can see the surface, and providing an image on the screen using the projector.
    Type: Grant
    Filed: March 2, 2010
    Date of Patent: September 1, 2015
    Assignee: VARIAN MEDICAL SYSTEMS, INC.
    Inventors: Andrew G. Jeung, Hassan Mostafavi
  • Patent number: 9008398
    Abstract: An image processing method includes: obtaining an input image; enhancing an object in the input image; and after the input image is enhanced, applying a low-pass filter using a processor to obtain a processed image. A computer product includes a non-transitory medium storing a set of instructions, an execution of which causes a method to be performed, the method comprising: obtaining an input image; enhancing an object in the input image; and after the input image is enhanced, applying a low-pass filter to obtain a processed image.
    Type: Grant
    Filed: October 26, 2012
    Date of Patent: April 14, 2015
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hassan Mostafavi, Alexander Sloutsky, Andrew G. Jeung
  • Publication number: 20140267773
    Abstract: A marker system includes: a first marker; and a second marker; wherein the first marker and the second marker are configured to emit light from one or more light sources coupled to the first marker and the second marker; and wherein the first marker and the second marker are configured to emit the light for detection by a camera. A method performed using a marker system includes: generating light using one or more light sources; emitting the light at a plurality of markers that are coupled to the light sources; and detecting the light emitted from the plurality of markers using a camera; wherein the act of detecting comprises using one or more filters to reduce ambient light to a level that corresponds with a noise level of the camera while allowing light emitted from the markers to be imaged by the camera.
    Type: Application
    Filed: September 27, 2013
    Publication date: September 18, 2014
    Applicant: Varian Medical Systems, Inc.
    Inventors: Andrew G. JEUNG, Hassan MOSTAFAVI, George A. ZDASIUK, Gary F. VIRSHUP, Dusan BAIC, Daniel R. BILSKY, Alexander R. BROWN, Jon CARVER, Graham FAULKNOR, Alyssa GARVER, Arthur KWUN, Michelle RICHMOND, Josh M. STAR-LACK, John G. VAN HETEREN
  • Publication number: 20140119623
    Abstract: An image processing method includes: obtaining an input image; enhancing an object in the input image; and after the input image is enhanced, applying a low-pass filter using a processor to obtain a processed image. A computer product includes a non-transitory medium storing a set of instructions, an execution of which causes a method to be performed, the method comprising: obtaining an input image; enhancing an object in the input image; and after the input image is enhanced, applying a low-pass filter to obtain a processed image.
    Type: Application
    Filed: October 26, 2012
    Publication date: May 1, 2014
    Inventors: Hassan MOSTAFAVI, Alexander SLOUTSKY, Andrew G. JEUNG
  • Publication number: 20140119631
    Abstract: A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.
    Type: Application
    Filed: October 26, 2012
    Publication date: May 1, 2014
    Inventors: Hassan MOSTAFAVI, Alexander SLOUTSKY, Andrew G. JEUNG
  • Patent number: 8417315
    Abstract: A marker system includes a structure having a first surface and a second surface, a first marker located on the first surface, and a second marker located on the second surface, wherein the first marker and the second marker are arranged so that they face approximately a same direction, and so that they can be simultaneously viewed by an optical device, and wherein a first distance between the first marker and the optical device is different from a second distance between the second marker and the optical device when the first and the second markers are simultaneously viewed by the optical device.
    Type: Grant
    Filed: May 14, 2007
    Date of Patent: April 9, 2013
    Assignee: Varian Medical Systems, Inc.
    Inventors: Hassan Mostafavi, Andrew G. Jeung
  • Patent number: 8198579
    Abstract: A calibration device includes a structure, and a target object that is moveably coupled to the structure, the target object being a physical target towards which an alignment device can be aimed. A calibration device includes a block having a first opening, and a target object that is viewable through the first opening. A method of calibrating an alignment device includes determining a target position associated with a machine, placing a target object at the target position, and adjusting the alignment device using the target object. A calibration device includes a target object, the target object being a physical target towards which an alignment device can be aimed, wherein the target object comprises a first feature for indicating a first orientation of the target object.
    Type: Grant
    Filed: October 30, 2006
    Date of Patent: June 12, 2012
    Assignee: Varian Medical Systems, Inc.
    Inventor: Andrew G. Jeung
  • Patent number: 8135205
    Abstract: A method for use in an object scanning process includes obtaining a reference spectrum that includes a plurality of reference peaks, and comparing the reference spectrum with an input spectrum that has a plurality of input peaks, wherein a number of the reference peaks is less than eight. A method for use in an object scanning process includes obtaining a reference spectrum that includes a plurality of reference peaks, comparing one of the reference peaks with a plurality of input peaks from an input spectrum, comparing another one of the reference peaks with the plurality of input peaks from the input spectrum, and determining a degree of similarity between the reference spectrum and the input spectrum using a result from the acts of comparing.
    Type: Grant
    Filed: December 20, 2008
    Date of Patent: March 13, 2012
    Assignee: Varian Medical Systems, Inc.
    Inventor: Andrew G. Jeung
  • Patent number: 7844094
    Abstract: A method of determining a geometric parameter of a machine includes using the machine to obtain an image of at least a portion of a structure, the structure having a plurality of markers, wherein the markers have predetermined position(s) relative to each other, determining a position of the structure based on a pattern of the markers in the image, and determining a geometric parameter of the machine based at least in part on the determined position of the structure.
    Type: Grant
    Filed: April 29, 2005
    Date of Patent: November 30, 2010
    Assignee: Varian Medical Systems, Inc.
    Inventors: Andrew G. Jeung, Hassan Mostafavi, Alexander Sloutsky
  • Publication number: 20100158385
    Abstract: A method for use in an object scanning process includes obtaining a reference spectrum that includes a plurality of reference peaks, and comparing the reference spectrum with an input spectrum that has a plurality of input peaks, wherein a number of the reference peaks is less than eight. A method for use in an object scanning process includes obtaining a reference spectrum that includes a plurality of reference peaks, comparing one of the reference peaks with a plurality of input peaks from an input spectrum, comparing another one of the reference peaks with the plurality of input peaks from the input spectrum, and determining a degree of similarity between the reference spectrum and the input spectrum using a result from the acts of comparing.
    Type: Application
    Filed: December 20, 2008
    Publication date: June 24, 2010
    Applicant: Varian Medical Systems, Inc.
    Inventor: Andrew G. Jeung