Patents by Inventor James A. Wheaton
James A. Wheaton 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: 11704785Abstract: Embodiments are directed to techniques for image content extraction. Some embodiments include extracting contextually structured data from document images, such as by automatically identifying document layout, document data, document metadata, and/or correlations therebetween in a document image, for instance. Some embodiments utilize breakpoints to enable the system to match different documents with internal variations to a common template. Several embodiments include extracting contextually structured data from table images, such as gridded and non-gridded tables. Many embodiments are directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. Several embodiments are directed to automatically identifying and associating document metadata with corresponding document data in a document image to generate a machine-facilitated annotation of the document image.Type: GrantFiled: August 17, 2022Date of Patent: July 18, 2023Assignee: SAS INSTITUTE INC.Inventors: David James Wheaton, Stuart Dakari Cooke, III, William Robert Nadolski
-
Publication number: 20230206427Abstract: An apparatus for magnetic resonance imaging includes processing circuitry to obtain a set of sequence instructions for performing a magnetic resonance scan; partition the obtained set of sequence instructions into a plurality of kernels by determining partition time points defining boundaries of the plurality of kernels, wherein the partition time points are not equally spaced in time; convert a first kernel of the plurality of kernels into a first hardware instruction set; transmit the first hardware instruction set to a hardware board controller for execution; and reconstruct a magnetic resonance image from received data, including data obtained by executing the first kernel.Type: ApplicationFiled: December 28, 2021Publication date: June 29, 2023Applicant: CANON MEDICAL SYSTEMS CORPORATIONInventors: Andrew JAMES WHEATON, Joseph MANAK, Bradley STEPHENS
-
Publication number: 20220392047Abstract: Embodiments are directed to techniques for image content extraction. Some embodiments include extracting contextually structured data from document images, such as by automatically identifying document layout, document data, document metadata, and/or correlations therebetween in a document image, for instance. Some embodiments utilize breakpoints to enable the system to match different documents with internal variations to a common template. Several embodiments include extracting contextually structured data from table images, such as gridded and non-gridded tables. Many embodiments are directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. Several embodiments are directed to automatically identifying and associating document metadata with corresponding document data in a document image to generate a machine-facilitated annotation of the document image.Type: ApplicationFiled: August 17, 2022Publication date: December 8, 2022Applicant: SAS Institute Inc.Inventors: David James Wheaton, Stuart Dakari Cooke, III, William Robert Nadolski
-
Patent number: 11443416Abstract: Various embodiments are generally directed to techniques for image content extraction. Some embodiments include extracting contextually structured data from document images, such as by automatically identifying document layout, document data, document metadata, and/or correlations therebetween in a document image, for instance. Several embodiments include extracting contextually structured data from table images, such as gridded and non-gridded tables. For example, the contents of cells may be extracted from a table image along with structural context including the corresponding row and column information. Many embodiments are directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. Several embodiments are directed to automatically identifying and associating document metadata with corresponding document data in a document image to generate a machine-facilitated annotation of the document image.Type: GrantFiled: August 9, 2021Date of Patent: September 13, 2022Assignee: SAS INSTITUTE INC.Inventors: Yi Liao, Charles Franklin Board, William Robert Nadolski, David James Wheaton, Heather Michelle Goodykoontz, Adheesha Sanjuaya Arangala, Karthik Nakkeeran
-
Patent number: 11389077Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.Type: GrantFiled: May 6, 2021Date of Patent: July 19, 2022Assignee: CANON MEDICAL SYSTEMS CORPORATIONInventors: Andrew James Wheaton, Antonios Matakos, Samir Dev Sharma
-
Patent number: 11255941Abstract: A method and apparatus are provided to perform controlled aliasing in parallel imaging (CAIPI) using time shifts between the radio frequency (RF) excitation pulses and the waveform of the slice-select gradient field to shift respective sampling points within the two-dimensions of k-space corresponding to phase encoding. Thus, a CAIPI sampling pattern is generated using time shifts, rather than by modulating the RF excitation pulses or gradient fields.Type: GrantFiled: April 17, 2020Date of Patent: February 22, 2022Assignee: CANON MEDICAL SYSTEMS CORPORATIONInventor: Andrew James Wheaton
-
Publication number: 20210366099Abstract: Various embodiments are generally directed to techniques for image content extraction. Some embodiments include extracting contextually structured data from document images, such as by automatically identifying document layout, document data, document metadata, and/or correlations therebetween in a document image, for instance. Several embodiments include extracting contextually structured data from table images, such as gridded and non-gridded tables. For example, the contents of cells may be extracted from a table image along with structural context including the corresponding row and column information. Many embodiments are directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. Several embodiments are directed to automatically identifying and associating document metadata with corresponding document data in a document image to generate a machine-facilitated annotation of the document image.Type: ApplicationFiled: August 9, 2021Publication date: November 25, 2021Applicant: SAS Institute Inc.Inventors: Yi Liao, Charles Franklin Board, William Robert Nadolski, David James Wheaton, Heather Michelle Goodykoontz, Adheesha Sanjuaya Arangala, Karthik Nakkeeran
-
Publication number: 20210325498Abstract: A method and apparatus are provided to perform controlled aliasing in parallel imaging (CAIPI) using time shifts between the radio frequency (RF) excitation pulses and the waveform of the slice-select gradient field to shift respective sampling points within the two-dimensions of k-space corresponding to phase encoding. Thus, a CAIPI sampling pattern is generated using time shifts, rather than by modulating the RF excitation pulses or gradient fields.Type: ApplicationFiled: April 17, 2020Publication date: October 21, 2021Applicant: CANON MEDICAL SYSTEMS CORPORATIONInventor: Andrew James WHEATON
-
Publication number: 20210315475Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.Type: ApplicationFiled: May 6, 2021Publication date: October 14, 2021Applicant: CANON MEDICAL SYSTEMS CORPORATIONInventors: Andrew James WHEATON, Antonios MATAKOS, Samir Dev SHARMA
-
Patent number: 11087077Abstract: Embodiments are generally directed to techniques for extracting contextually structured data from document images, such as by automatically identifying document layout, document data, and/or document metadata in a document image, for instance. Many embodiments are particularly directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. For example, the document template database may include a plurality of templates for identifying/explaining key data elements in various document image formats that can be used to extract contextually structured data from incoming document images with a matching document image format. Several embodiments are particularly directed to automatically identifying and associating document metadata with corresponding document data in a document image, such as for generating a machine-facilitated annotation of the document image.Type: GrantFiled: November 5, 2020Date of Patent: August 10, 2021Assignee: SAS INSTITUTE INC.Inventors: David James Wheaton, William Robert Nadolski, Heather Michelle GoodyKoontz
-
Patent number: 11064901Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.Type: GrantFiled: March 29, 2019Date of Patent: July 20, 2021Assignee: CANON MEDICAL SYSTEMS CORPORATIONInventors: Andrew James Wheaton, Antonios Matakos, Samir Dev Sharma
-
Publication number: 20210200937Abstract: Embodiments are generally directed to techniques for extracting contextually structured data from document images, such as by automatically identifying document layout, document data, and/or document metadata in a document image, for instance. Many embodiments are particularly directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. For example, the document template database may include a plurality of templates for identifying/explaining key data elements in various document image formats that can be used to extract contextually structured data from incoming document images with a matching document image format. Several embodiments are particularly directed to automatically identifying and associating document metadata with corresponding document data in a document image, such as for generating a machine-facilitated annotation of the document image.Type: ApplicationFiled: November 5, 2020Publication date: July 1, 2021Applicant: SAS Institute Inc.Inventors: David James Wheaton, William Robert Nadolski, Heather Michelle GoodyKoontz
-
Patent number: 11049235Abstract: Embodiments are generally directed to techniques for extracting contextually structured data from document images, such as by automatically identifying document layout, document data, and/or document metadata in a document image, for instance. Many embodiments are particularly directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. For example, the document template database may include a plurality of templates for identifying/explaining key data elements in various document image formats that can be used to extract contextually structured data from incoming document images with a matching document image format. Several embodiments are particularly directed to automatically identifying and associating document metadata with corresponding document data in a document image, such as for generating a machine-facilitated annotation of the document image.Type: GrantFiled: October 29, 2020Date of Patent: June 29, 2021Assignee: SAS INSTITUTE INC.Inventors: David James Wheaton, William Robert Nadolski, Heather Michelle GoodyKoontz
-
Patent number: 11041927Abstract: An apparatus and method of detecting a characteristic in an image is performed by obtaining, from an image capturing apparatus, raw signal data formed from a plurality of data samples and including a signal of interest captured by the image capturing apparatus and classifying, using a neural network, samples other than the signal of interest using a classifier having been determined using a first parameter based on information about the sample and a second parameter based on information identifying a position of the sample within the raw image data.Type: GrantFiled: May 13, 2020Date of Patent: June 22, 2021Assignee: CANON MEDICAL SYSTEMS CORPORATIONInventors: Andrew James Wheaton, Anuj Sharma
-
Publication number: 20210110527Abstract: Embodiments are generally directed to techniques for extracting contextually structured data from document images, such as by automatically identifying document layout, document data, and/or document metadata in a document image, for instance. Many embodiments are particularly directed to generating and utilizing a document template database for automatically extracting document image contents into a contextually structured format. For example, the document template database may include a plurality of templates for identifying/explaining key data elements in various document image formats that can be used to extract contextually structured data from incoming document images with a matching document image format. Several embodiments are particularly directed to automatically identifying and associating document metadata with corresponding document data in a document image, such as for generating a machine-facilitated annotation of the document image.Type: ApplicationFiled: October 29, 2020Publication date: April 15, 2021Applicant: SAS Institute Inc.Inventors: David James Wheaton, William Robert Nadolski, Heather Michelle GoodyKoontz
-
Publication number: 20200305756Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.Type: ApplicationFiled: March 29, 2019Publication date: October 1, 2020Applicant: Canon Medical Systems CorporationInventors: Andrew James Wheaton, Antonios Matakos, Samir Dev Sharma
-
Patent number: 10578701Abstract: An MRI system includes processing circuitry configured to generate two or more RF pulses to form a spin echo, wherein each RF pulse corresponds to selecting at least two slice locations. Additionally, the MRI system encodes magnetic resonance (MR) magnetization to form echo signal data for each RF pulse, applies a set of time-shifts to a slice-selection gradient for each selected slice location, generates a pattern of slice-position-dependent moments on the echo signal data based on the set of time-shifts to the slice-selection gradient, receives image data corresponding to the echo signal data, and reconstructs the image data to form a plurality of images, wherein each of the plurality of images corresponds to one of the selected slice locations.Type: GrantFiled: October 24, 2017Date of Patent: March 3, 2020Assignee: Canon Medical Systems CorporationInventor: Andrew James Wheaton
-
Patent number: 10416267Abstract: An apparatus and method are disclosed for determining a time origin of an input RF pulse of a plurality of input RF pulses. The method includes generating an RF echo based on the plurality of input RF pulses, a time-duration between the input RF pulses being controllable in order to determine a time instance corresponding to an ideal position of the RF echo. The method further includes acquiring a data signal corresponding to a scan of a subject, and computing a time-difference between a measured peak of the acquired data signal and the time instance corresponding to the ideal position of the RF echo, the computed time difference corresponding to a measure of a time-shift of an effective magnetic center of the input RF pulse.Type: GrantFiled: January 9, 2017Date of Patent: September 17, 2019Assignee: Canon Medical Systems CorporationInventors: Andrew James Wheaton, Michael R. Thompson
-
Publication number: 20190120922Abstract: An MRI system includes processing circuitry configured to generate two or more RF pulses to form a spin echo, wherein each RF pulse corresponds to selecting at least two slice locations. Additionally, the MRI system encodes magnetic resonance (MR) magnetization to form echo signal data for each RF pulse, applies a set of time-shifts to a slice-selection gradient for each selected slice location, generates a pattern of slice-position-dependent moments on the echo signal data based on the set of time-shifts to the slice-selection gradient, receives image data corresponding to the echo signal data, and reconstructs the image data to form a plurality of images, wherein each of the plurality of images corresponds to one of the selected slice locations.Type: ApplicationFiled: October 24, 2017Publication date: April 25, 2019Applicant: Toshiba Medical Systems CorporationInventor: Andrew James WHEATON
-
Patent number: 10025841Abstract: A method and system for playlist generation is disclosed. In one aspect, the system may include at least one analysis module for receiving and analyzing an unknown work and generating a corresponding representation thereof, and at least one identification (ID) server for receiving the representation from the analysis modules and determining the identity of the unknown work.Type: GrantFiled: January 30, 2015Date of Patent: July 17, 2018Assignee: Audible Magic, Inc.Inventors: James B. Schrempp, Vance Ikezoye, Erling H. Wold, Thomas L. Blum, Douglas F. Keislar, James A. Wheaton