Patents by Inventor Benjamin Austin

Benjamin Austin 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: 11646119
    Abstract: This disclosure relates to detecting visual findings in anatomical images. Methods comprise inputting anatomical images into a neural network to output a feature vector and computing an indication of visual findings being present in the images by a dense layer of the neural network that takes as input the feature vector and outputs an indication of whether each of the visual findings is present in the anatomical images. The neural network is trained on a training dataset including anatomical images, and labels associated with the anatomical images and each of the visual findings. The visual findings may be organised as a hierarchical ontology tree. The neural network may be trained by evaluating the performance of neural networks in detecting the visual findings and a negation pair class which comprises anatomical images where a first visual finding is identified in the absence of a second visual finding.
    Type: Grant
    Filed: June 9, 2021
    Date of Patent: May 9, 2023
    Assignee: Annalise AI Pty Ltd
    Inventors: Dang-Dinh-Ang Tran, Jarrel Seah, David Huang, David Vuong, Xavier Holt, Marc Justin Nothrop, Benjamin Austin, Aaron Lee, Marco Amoroso
  • Publication number: 20230089026
    Abstract: This disclosure relates to detecting visual findings in anatomical images. Methods comprise inputting anatomical images into a neural network to output a feature vector and computing an indication of visual findings being present in the images by a dense layer of the neural network that takes as input the feature vector and outputs an indication of whether each of the visual findings is present in the anatomical images. The neural network is trained on a training dataset including anatomical images, and labels associated with the anatomical images and each of the visual findings. The visual findings may be organised as a hierarchical ontology tree. The neural network may be trained by evaluating the performance of neural networks in detecting the visual findings and a negation pair class which comprises anatomical images where a first visual finding is identified in the absence of a second visual finding.
    Type: Application
    Filed: June 9, 2021
    Publication date: March 23, 2023
    Applicant: Annalise-AI Pty Ltd
    Inventors: Dang-Dinh-Ang TRAN, Jarrel SEAH, David HUANG, David VUONG, Xavier HOLT, Marc Justin NOTHROP, Benjamin AUSTIN, Aaron LEE, Marco AMOROSO
  • Patent number: 4141273
    Abstract: A device is provided for learning and practicing a musical beat. A foot pedal is adjustably connected by linkages and springs to actuate switches to produce one signal when the pedal is at a selected downward position and another signal when the pedal is at a selected upward position. Visual readout means located adjacent the sheet music used by a player receives the signal and flashes one kind of light adjacent the music when the pedal has reached its upbeat, and another kind of light adjacent the music when the pedal has reached its down beat. The pedal is rotatably adjustable to accommodate all methods of keeping time with the foot.
    Type: Grant
    Filed: January 16, 1978
    Date of Patent: February 27, 1979
    Inventor: Benjamin Austin