Patents by Inventor Guang-Hong Chen

Guang-Hong Chen 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: 11908044
    Abstract: Methods and systems are provided for increasing a quality of computed tomography (CT) images reconstructed from high helical pitch scans. In one embodiment, the current disclosure provides for a method comprising generating a first computed tomography (CT) image from projection data acquired at a high helical pitch; using a trained multidimensional statistical regression model to generate a second CT image from the first CT image, the multidimensional statistical regression model trained with a plurality of target CT images reconstructed from projection data acquired at a lower helical pitch; and performing an iterative correction of the second CT image to generate a final CT image.
    Type: Grant
    Filed: June 17, 2021
    Date of Patent: February 20, 2024
    Assignees: GE PRECISION HEALTHCARE LLC, WISCONSIN ALUMNI RESEARCH FOUNDATION
    Inventors: Guang-Hong Chen, Jiang Hsieh
  • Patent number: 11826190
    Abstract: A system and method for generating reports on perfusion blood volume from computed tomography (CT) data acquired from a subject. The method includes receiving multi-faceted CT data acquired from the subject using one of a multi-energy or polychromatic CT acquisition and deriving an iodine concentration in an artery feeding a volume of interest (VOI) in the multi-faceted CT data. The method further includes determining an effective atomic number of a spatial distribution in the VOL calculating a perfused blood volume of the VOI using the iodine concentration and the effective atomic number, and generating a report of the perfused blood volume of the VOI.
    Type: Grant
    Filed: July 14, 2021
    Date of Patent: November 28, 2023
    Assignee: WISCONSIN ALUMNI RESEARCH FOUNDATION
    Inventors: Guang-Hong Chen, Ke Li, Thomas Grist
  • Publication number: 20230132514
    Abstract: A system and method for creating computed tomography (CT) images includes acquiring or accessing sinogram data and determining a photon count for the sinogram data. The method includes generating unbiased sinogram data from the sinogram data using an unbiased estimator and the photon count and reconstructing a CT image from the unbiased sinogram data.
    Type: Application
    Filed: October 27, 2021
    Publication date: May 4, 2023
    Inventors: Guang-Hong Chen, Ke Li
  • Publication number: 20230026268
    Abstract: A system and method for generating reports on perfusion blood volume from computed tomography (CT) data acquired from a subject. The method includes receiving multi-faceted CT data acquired from the subject using one of a multi-energy or polychromatic CT acquisition and deriving an iodine concentration in an artery feeding a volume of interest (VOI) in the multi-faceted CT data. The method further includes determining an effective atomic number of a spatial distribution in the VOL calculating a perfused blood volume of the VOI using the iodine concentration and the effective atomic number, and generating a report of the perfused blood volume of the VOI.
    Type: Application
    Filed: July 14, 2021
    Publication date: January 26, 2023
    Inventors: Guang-Hong Chen, Ke Li, Thomas Grist
  • Publication number: 20220405990
    Abstract: Methods and systems are provided for increasing a quality of computed tomography (CT) images reconstructed from high helical pitch scans. In one embodiment, the current disclosure provides for a method comprising generating a first computed tomography (CT) image from projection data acquired at a high helical pitch; using a trained multidimensional statistical regression model to generate a second CT image from the first CT image, the multidimensional statistical regression model trained with a plurality of target CT images reconstructed from projection data acquired at a lower helical pitch; and performing an iterative correction of the second CT image to generate a final CT image.
    Type: Application
    Filed: June 17, 2021
    Publication date: December 22, 2022
    Inventors: Guang-Hong Chen, Jiang Hsieh
  • Patent number: 11420075
    Abstract: A system and method for acquiring medical images of a subject includes performing two-dimensional (2D) scan of a subject using a medical imaging system to acquire 2D data from at least two view angles and generating a three-dimensional (3D) model of the subject from the 2D data. The method also includes extracting desired images of the subject from the 3D model. The desired images are at view angles different from the at least two view angles. The method further includes prescribing an imaging study of the subject using the desired images of the subject to control at least one of a signal-to-noise ratio of data acquired using the imaging study or a dose of ionizing radiation delivered to the subject during the imaging study. The method also includes performing the imaging study using the medical imaging system to acquire imaging data from the subject and reconstructing images of the subject from the imaging data.
    Type: Grant
    Filed: September 20, 2019
    Date of Patent: August 23, 2022
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Juan Camilo Montoya, Thomas M. Grist
  • Patent number: 11350895
    Abstract: A system and method for material decomposition of a single energy spectrum x-ray dataset includes accessing the single energy spectrum x-ray dataset, receiving a user-selection of a desired energy for decomposition, and decomposing the single energy spectrum x-ray dataset into material bases as a linear combination of energy dependence function of selected basis materials and the corresponding spatial dependence material bases images.
    Type: Grant
    Filed: November 29, 2019
    Date of Patent: June 7, 2022
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Yinsheng Li
  • Patent number: 11062489
    Abstract: A system and method for reconstructing an image of a subject acquired using a tomographic imaging system includes at least one computer processor configured to form an image reconstruction pipeline. The reconstruction pipeline at least includes an automated correction module configured to receive imaging data acquired from a subject using ionizing radiation generated by the tomographic imaging system and generate corrected data using a first learning network. The reconstruction pipeline also includes an intelligent reconstruction module configured to receive at least one of the imaging data and the corrected data and reconstruct an image of the subject using a second learning network.
    Type: Grant
    Filed: February 13, 2019
    Date of Patent: July 13, 2021
    Assignee: WISCONSIN ALUMNI RESEARCH FOUNDATION
    Inventors: Guang-Hong Chen, Yinsheng Li
  • Publication number: 20210161487
    Abstract: A system and method for material decomposition of a single energy spectrum x-ray dataset includes accessing the single energy spectrum x-ray dataset, receiving a user-selection of a desired energy for decomposition, and decomposing the single energy spectrum x-ray dataset into material bases as a linear combination of energy dependence function of selected basis materials and the corresponding spatial dependence material bases images.
    Type: Application
    Filed: November 29, 2019
    Publication date: June 3, 2021
    Applicant: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Yinsheng Li
  • Publication number: 20200094074
    Abstract: A system and method for acquiring medical images of a subject includes performing two-dimensional (2D) scan of a subject using a medical imaging system to acquire 2D data from at least two view angles and generating a three-dimensional (3D) model of the subject from the 2D data. The method also includes extracting desired images of the subject from the 3D model. The desired images are at view angles different from the at least two view angles. The method further includes prescribing an imaging study of the subject using the desired images of the subject to control at least one of a signal-to-noise ratio of data acquired using the imaging study or a dose of ionizing radiation delivered to the subject during the imaging study. The method also includes performing the imaging study using the medical imaging system to acquire imaging data from the subject and reconstructing images of the subject from the imaging data.
    Type: Application
    Filed: September 20, 2019
    Publication date: March 26, 2020
    Applicant: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Juan Camilo Montoya, Thomas M. Grist
  • Patent number: 10517556
    Abstract: A method for increasing the temporal fidelity, increasing the temporal sampling density, and/or reducing the temporal noise of a series of image frames obtained with a medical imaging system is provided. The image frames are acquired with the medical imaging system. The medical imaging system may be, for example, an x-ray C-arm imaging system. A window function that is representative of a temporal fidelity window is selected and used to temporally deconvolve the image frames using a minimization technique. A temporal sampling density may also be selected and used in the temporal deconvolution. The resultant deconvolved image frames have a higher temporal fidelity to a time-varying image contrast depicted in the acquired image frames, and may also have an increased temporal sampling density and/or reduced temporal noise.
    Type: Grant
    Filed: February 8, 2013
    Date of Patent: December 31, 2019
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Jie Tang
  • Patent number: 10417793
    Abstract: A system and method for reconstructing an image of a subject includes acquiring a reference dataset and reconstructing a prior image of the subject from the reference dataset and selecting at least a portion of the prior image that corresponds to a portion of the prior image of the subject that is free of artifacts. The method also includes acquiring a medical imaging dataset of the subject, performing a vertical comparison of the medical imaging dataset and the reference dataset to create a data inconsistency metric, and repeating the preceding steps to create a plurality of data inconsistency metrics. The method further includes performing a horizontal comparison of the data inconsistency metrics to identify inconsistent data, compensating for the inconsistent data, and reconstructing an image of the subject with reduced artifacts compared to the prior image.
    Type: Grant
    Filed: March 23, 2017
    Date of Patent: September 17, 2019
    Assignee: Wisconsin Alumni Research Foundation
    Inventor: Guang-Hong Chen
  • Publication number: 20190251713
    Abstract: A system and method for reconstructing an image of a subject acquired using a tomographic imaging system includes at least one computer processor configured to form an image reconstruction pipeline. The reconstruction pipeline at least includes an automated correction module configured to receive imaging data acquired from a subject using ionizing radiation generated by the tomographic imaging system and generate corrected data using a first learning network. The reconstruction pipeline also includes an intelligent reconstruction module configured to receive at least one of the imaging data and the corrected data and reconstruct an image of the subject using a second learning network.
    Type: Application
    Filed: February 13, 2019
    Publication date: August 15, 2019
    Inventors: Guang-Hong Chen, Yinsheng Li
  • Patent number: 10332281
    Abstract: Systems and methods for generating one or more denoised images from a series of noisy images acquired with a medical imaging system are described. In general, the systems and methods described here implement techniques whereby the series of noisy images are formed into a spatial-temporal or spatial-spectral image matrix in which each column represents a different noisy image. The image matrix is then processed to decompose the image matrix into basis images defined by a spatial and a temporal or spectral basis. Low rank solutions are enforced and extracted from the resulting decomposed image matrix as denoised images.
    Type: Grant
    Filed: January 29, 2016
    Date of Patent: June 25, 2019
    Assignee: Wisconsin Alumni Research Foundation
    Inventor: Guang-Hong Chen
  • Patent number: 10147207
    Abstract: A system and method for reconstructing an image using a cone-beam computed tomography (CT) imaging system includes acquiring data from a subject with the CT imaging system using a limited scan range that is less than 360 degrees. The process also includes reconstructing at least one image of the subject having a first temporal resolution from the data acquired, performing a temporal deconvolution of the at least one image using a finite temporal window to generate at least one image of the subject with a second temporal resolution that is greater than the first temporal resolution, and subtracting the at least one image of the subject with the second temporal resolution and a mask image of the subject to generate a time-resolved CT angiogram of the subject.
    Type: Grant
    Filed: July 15, 2016
    Date of Patent: December 4, 2018
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Guang-Hong Chen, Charles Strother
  • Patent number: 10140734
    Abstract: Described here is a system and method for image reconstruction that can automatically and iteratively produce multiple images from one set of acquired data, in which each of these multiple images corresponds to a subset of the acquired data that is self-consistent, but inconsistent with other subsets of the acquired data. The image reconstruction includes iteratively minimizing the rank of an image matrix whose columns each correspond to a different image, and in which one column corresponds to a user-provided prior image of the subject. The rank minimization is constrained subject to a consistency condition that enforces consistency between the forward projection of each column in the image matrix and a respective subset of the acquired data that contains data that is consistent with data in the subset, but inconsistent with data not in the subset.
    Type: Grant
    Filed: January 29, 2016
    Date of Patent: November 27, 2018
    Assignee: Wisconsin Alumni Research Foundation
    Inventor: Guang-Hong Chen
  • Publication number: 20180276852
    Abstract: A system and method for reconstructing an image of a subject includes acquiring a reference dataset and reconstructing a prior image of the subject from the reference dataset and selecting at least a portion of the prior image that corresponds to a portion of the prior image of the subject that is free of artifacts. The method also includes acquiring a medical imaging dataset of the subject, performing a vertical comparison of the medical imaging dataset and the reference dataset to create a data inconsistency metric, and repeating the preceding steps to create a plurality of data inconsistency metrics. The method further includes performing a horizontal comparison of the data inconsistency metrics to identify inconsistent data, compensating for the inconsistent data, and reconstructing an image of the subject with reduced artifacts compared to the prior image.
    Type: Application
    Filed: March 23, 2017
    Publication date: September 27, 2018
    Inventor: Guang-Hong Chen
  • Patent number: 9958262
    Abstract: A system for measuring the profile or the refractive index of a transparent object by fringe projection techniques is provided and has an image generating device, an image capture device, and an image processor. The image generating device produces a reference image with a long depth of focus. This reference image is emitted into an inspected transparent object, and is distorted by the refractive index and the profile of the transparent object. The image capture device receives the distorted image. The image processor analyzes the difference between the distorted image and the reference image, so as to identify the profile or the refractive index of the inspected transparent object.
    Type: Grant
    Filed: August 24, 2015
    Date of Patent: May 1, 2018
    Assignee: NATIONAL SUN YAT-SEN UNIVERSITY
    Inventors: Wei-Hung Su, Chau-Jern Cheng, Guang-Hong Chen
  • Publication number: 20180018796
    Abstract: A system and method for reconstructing an image using a cone-beam computed tomography (CT) imaging system includes acquiring data from a subject with the CT imaging system using a limited scan range that is less than 360 degrees. The process also includes reconstructing at least one image of the subject having a first temporal resolution from the data acquired, performing a temporal deconvolution of the at least one image using a finite temporal window to generate at least one image of the subject with a second temporal resolution that is greater than the first temporal resolution, and subtracting the at least one image of the subject with the second temporal resolution and a mask image of the subject to generate a time-resolved CT angiogram of the subject.
    Type: Application
    Filed: July 15, 2016
    Publication date: January 18, 2018
    Inventors: Guang-Hong Chen, Charles Strother
  • Publication number: 20170221234
    Abstract: Systems and methods for generating one or more denoised images from a series of noisy images acquired with a medical imaging system are described. In general, the systems and methods described here implement techniques whereby the series of noisy images are formed into a spatial-temporal or spatial-spectral image matrix in which each column represents a different noisy image. The image matrix is then processed to decompose the image matrix into basis images defined by a spatial and a temporal or spectral basis. Low rank solutions are enforced and extracted from the resulting decomposed image matrix as denoised images.
    Type: Application
    Filed: January 29, 2016
    Publication date: August 3, 2017
    Inventor: Guang-Hong Chen