Patents by Inventor Andriy Myronenko

Andriy Myronenko 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: 20210374502
    Abstract: Apparatuses, systems, and techniques to select a nueral network architecture from a plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a neural network is trained by combining training resutls from different FL computing systesms, where each of the different FL computing systems, for example, trains different portions of the nerual network.
    Type: Application
    Filed: June 1, 2020
    Publication date: December 2, 2021
    Inventors: Holger Reinhard Roth, Dong Yang, Wenqi Li, Andriy Myronenko, Wentao Zhu, Ziyue Xu, Xiaosong Wang, Daguang Xu
  • Patent number: 11185715
    Abstract: A method of image-guided radiation treatment is described. The method may include acquiring a pre-treatment image of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level. The method may also include processing the first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, and wherein part or all of the image data comprises the target. The method may also include registering the enhanced image with the pre-treatment image to obtain a registration result and tracking movement and position of the target using the registration result to generate tracking information.
    Type: Grant
    Filed: October 28, 2020
    Date of Patent: November 30, 2021
    Assignee: Accuray Incorporated
    Inventors: Petr Jordan, Andriy Myronenko, Jay B. West, Calvin R. Maurer, Prashant Chopra, Anuj K. Purwar, Christopher A. Janko
  • Publication number: 20210334975
    Abstract: Apparatuses, systems, and techniques are presented to predict segmentations for objects in images. In at least one embodiment, a neural network is trained to determine one or more segmentation masks corresponding to one or more objects of one or more digital images based, at least in part, on one or more boundary regions of the one or more objects.
    Type: Application
    Filed: April 23, 2020
    Publication date: October 28, 2021
    Inventors: Dong Yang, Holger Roth, Xiaosong Wang, Ziyue Xu, Andriy Myronenko, Daguang Xu
  • Publication number: 20210049757
    Abstract: Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.
    Type: Application
    Filed: August 14, 2019
    Publication date: February 18, 2021
    Inventors: Wentao Zhu, Daguang Xu, Andriy Myronenko, Ziyue Xu
  • Publication number: 20210038918
    Abstract: A method of image-guided radiation treatment is described. The method may include acquiring a pre-treatment image of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level. The method may also include processing the first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, and wherein part or all of the image data comprises the target. The method may also include registering the enhanced image with the pre-treatment image to obtain a registration result and tracking movement and position of the target using the registration result to generate tracking information.
    Type: Application
    Filed: October 28, 2020
    Publication date: February 11, 2021
    Inventors: Petr Jordan, Andriy Myronenko, Jay B. West, Calvin R. Maurer, Prashant Chopra, Anuj K. Purwar, Christopher A. Janko
  • Publication number: 20210031052
    Abstract: A method of operating a radiation apparatus is described that selects at least a first angle and a second angle from the set of angles for a first rotation of the gantry. The method generates, using an imaging device mounted to the gantry, a first tracking image of the target from the first angle during the first rotation of the gantry. The method generates, using the imaging device, a second tracking image of the target from the second angle during the first rotation of the gantry. The method performs targeting tracking based on the first tracking image and the second tracking image.
    Type: Application
    Filed: October 13, 2020
    Publication date: February 4, 2021
    Inventors: Petr Jordan, Andriy Myronenko, Calvin Maurer, Eric Schnarr, Rob O'Connell
  • Publication number: 20210012504
    Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.
    Type: Application
    Filed: June 26, 2020
    Publication date: January 14, 2021
    Inventor: Andriy Myronenko
  • Patent number: 10843010
    Abstract: A method of image-guided radiation treatment is described. The method may include acquiring digitally reconstructed radiographs (DRRs) of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level. The method may also include processing the first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, and wherein part or all of the image data comprises the target. The method may also include registering the enhanced image with the DRRs to obtain a registration result, tracking movement and position of the target using the registration result to generating tracking information.
    Type: Grant
    Filed: November 11, 2019
    Date of Patent: November 24, 2020
    Assignee: Accuray Incorporated
    Inventors: Petr Jordan, Andriy Myronenko, Jay B. West, Calvin R. Maurer, Prashant Chopra, Anuj K. Purwar, Christopher A. Janko
  • Patent number: 10806948
    Abstract: A radiation therapy apparatus determines a set of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion. During an alignment phase or a treatment phase for a treatment stage of a target by the radiation therapy apparatus, the radiation therapy apparatus performs selects at least a first angle and a second angle from the set of angles for a first rotation of the gantry. The radiation therapy apparatus generates, using an imaging device mounted to the gantry, a first tracking image of the target from the first angle during the first rotation of the gantry. The radiation therapy apparatus generates, using the imaging device, a second tracking image of the target from the second angle during the first rotation of the gantry. The radiation therapy apparatus performs the target tracking based on the first tracking image and the second tracking image.
    Type: Grant
    Filed: October 7, 2019
    Date of Patent: October 20, 2020
    Assignee: Accuray Incorporated
    Inventors: Petr Jordan, Andriy Myronenko, Calvin Maurer, Eric Schnarr, Rob O'Connell
  • Publication number: 20200320722
    Abstract: A method of the present disclosure includes performing, by a processing device, a first image registration between a reference image of a patient and a motion image of the patient to perform alignment between the reference image and the motion image, wherein the reference image and the motion image include a target position of the patient. The method further includes performing, by the processing device, a second image registration between the reference image and a motion x-ray image of the patient, via a first digitally reconstructed radiograph (DRR) for the reference image of the patient. The method further includes tracking at least a translational change in the target position based on the first registration and the second registration.
    Type: Application
    Filed: June 22, 2020
    Publication date: October 8, 2020
    Inventors: Petr Jordan, Calvin R. Maurer, JR., Andriy Myronenko, Jonathan Cecil Chappelow
  • Publication number: 20200293828
    Abstract: Apparatuses, systems, and techniques to perform training of neural networks using stacked transformed images. In at least one embodiment, a neural network is trained on stacked transformed images and trained neural network is provided to be used for processing images from an unseen domain distinct from a source domain, wherein stacked transformed images are transformed according to transformation aspects related to domain variations.
    Type: Application
    Filed: March 9, 2020
    Publication date: September 17, 2020
    Inventors: Xiaosong Wang, Ziyue Xu, Dong Yang, Holger Reinhard Roth, Andriy Myronenko, Daguang Xu, Ling Zhang
  • Patent number: 10758748
    Abstract: A method includes determining a first estimate of leaf positions for a plurality of leaves of a multi-leaf collimator (MLC) in a reference coordinate space based on an image generated by an image-based aperture verification system, wherein the leaf positions for the plurality of leaves define an aperture for the MLC. The method further includes determining a second estimate of the leaf positions for the plurality of leaves in the reference coordinate space based on data from an additional source. The method further includes verifying the leaf positions for the plurality of leaves based on comparing the first estimate to the second estimate, wherein the leaf positions are verified if the first estimate deviates from the second estimate by less than a threshold value.
    Type: Grant
    Filed: March 8, 2018
    Date of Patent: September 1, 2020
    Assignee: Accuray Incorporated
    Inventors: Jonathan Cecil Chappelow, Petr Jordan, Calvin Maurer, Sarbjit Singh, Andrew W. Fitting, Andriy Myronenko, Jian Gao
  • Patent number: 10740901
    Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.
    Type: Grant
    Filed: December 17, 2018
    Date of Patent: August 11, 2020
    Assignee: NVIDIA CORPORATION
    Inventor: Andriy Myronenko
  • Patent number: 10713801
    Abstract: A method of the present disclosure includes performing, by a processing device, a first image registration between a reference image of a patient and a motion image of the patient to perform alignment between the reference image and the motion image, wherein the reference image and the motion image include a target position of the patient. The method further includes performing, by the processing device, a second image registration between the reference image and a motion x-ray image of the patient, via a first digitally reconstructed radiograph (DRR) for the reference image of the patient. The method further includes tracking at least a translational change in the target position based on the first registration and the second registration.
    Type: Grant
    Filed: January 4, 2018
    Date of Patent: July 14, 2020
    Assignee: Accuray Incorporated
    Inventors: Petr Jordan, Calvin R. Maurer, Jr., Andriy Myronenko, Jonathan Cecil Chappelow
  • Publication number: 20200193604
    Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.
    Type: Application
    Filed: December 17, 2018
    Publication date: June 18, 2020
    Inventor: Andriy Myronenko
  • Publication number: 20200121952
    Abstract: A processing device determines a plurality of angles from which tracking images can be generated by an imaging device. The processing device generates a plurality of projections of a treatment planning image of a patient, the treatment planning image comprising a delineated target, wherein each projection of the plurality of projections has an angle that corresponds to one of the plurality of angles from which the tracking images can be taken. The processing device determines, for each angle of the plurality of angles, a value of a tracking quality metric for tracking the target based on an analysis of a projection generated at that angle. The processing device selects a subset of the plurality of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion.
    Type: Application
    Filed: December 19, 2019
    Publication date: April 23, 2020
    Inventors: Petr Jordan, Andriy Myronenko, Calvin Maurer, Eric Schnarr, Rob O'Connell
  • Publication number: 20200094075
    Abstract: A method of image-guided radiation treatment is described. The method may include acquiring digitally reconstructed radiographs (DRRs) of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level. The method may also include processing the first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, and wherein part or all of the image data comprises the target. The method may also include registering the enhanced image with the DRRs to obtain a registration result, tracking movement and position of the target using the registration result to generating tracking information.
    Type: Application
    Filed: November 11, 2019
    Publication date: March 26, 2020
    Inventors: Petr Jordan, Andriy Myronenko, Jay B. West, Calvin R. Maurer, Prashant Chopra, Anuj K. Purwar, Christopher A. Janko
  • Publication number: 20200047000
    Abstract: A radiation therapy apparatus determines a set of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion. During an alignment phase or a treatment phase for a treatment stage of a target by the radiation therapy apparatus, the radiation therapy apparatus performs selects at least a first angle and a second angle from the set of angles for a first rotation of the gantry. The radiation therapy apparatus generates, using an imaging device mounted to the gantry, a first tracking image of the target from the first angle during the first rotation of the gantry. The radiation therapy apparatus generates, using the imaging device, a second tracking image of the target from the second angle during the first rotation of the gantry. The radiation therapy apparatus performs the target tracking based on the first tracking image and the second tracking image.
    Type: Application
    Filed: October 7, 2019
    Publication date: February 13, 2020
    Inventors: Petr Jordan, Andriy Myronenko, Calvin Maurer, Eric Schnarr, Rob O'Connell
  • Patent number: 10532224
    Abstract: A processing device determines a plurality of angles from which tracking images can be generated by an imaging device. The processing device generates a plurality of projections of a treatment planning image of a patient, the treatment planning image comprising a delineated target, wherein each projection of the plurality of projections has an angle that corresponds to one of the plurality of angles from which the tracking images can be taken. The processing device determines, for each angle of the plurality of angles, a value of a tracking quality metric for tracking the target based on an analysis of a projection generated at that angle. The processing device selects a subset of the plurality of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion.
    Type: Grant
    Filed: August 29, 2016
    Date of Patent: January 14, 2020
    Assignee: ACCURAY INCORPORATED
    Inventors: Petr Jordan, Andriy Myronenko, Calvin Maurer, Eric Schnarr, Rob O'Connell
  • Patent number: 10485989
    Abstract: A method of image-guided radiation treatment is described. The method may include acquiring digitally reconstructed radiographs (DRRs) of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level, wherein the first energy level is an energy level selected within the range of 50-100 kV and the second energy level is an energy level selected within the range of 100-150 kV. The method ma also include processing the first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, and wherein part or all of the image data comprises the target.
    Type: Grant
    Filed: July 12, 2016
    Date of Patent: November 26, 2019
    Assignee: ACCURAY INCORPORATED
    Inventors: Petr Jordan, Andriy Myronenko, Jay B. West, Calvin R. Maurer, Prashant Chopra, Anuj K. Purwar, Chris Janko