US 12,251,267 B2
Method and system for identifying a tendon in ultrasound imaging data and verifying such identity in live deployment
Kris Dickie, Vancouver (CA); Nishant Uniyal, Vancouver (CA); and Parisa Asgharzadeh, Vancouver (CA)
Assigned to Clarius Mobile Health Corp., Vancouver (CA)
Filed by Clarius Mobile Health Corp., Vancouver (CA)
Filed on Jun. 25, 2021, as Appl. No. 17/359,453.
Prior Publication US 2022/0409181 A1, Dec. 29, 2022
Int. Cl. A61B 8/00 (2006.01); A61B 8/08 (2006.01); G06N 3/047 (2023.01); G06N 3/08 (2023.01)
CPC A61B 8/5207 (2013.01) [A61B 8/08 (2013.01); A61B 8/461 (2013.01); A61B 8/468 (2013.01); G06N 3/047 (2023.01); G06N 3/08 (2013.01); G06V 2201/03 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method for identifying a tendon in ultrasound imaging data, the method comprising:
deploying an artificial intelligence (AI) model to execute on a computing device, wherein the AI model is trained to identify a plurality of different types of tendons imaged in ultrasound imaging data and when deployed, the computing device generates a probability for each of the plurality of different types of tendons that a type of tendon is imaged in new ultrasound imaging data;
receiving at least one user input at the computing device, the at least one user input indicating a type of the plurality of different types of tendons desired to be scanned, hereinafter, the selected tendon, wherein the at least one user input is selected from the group consisting of i) user selection of a preset comprising the selected tendon; ii) user selection of a workflow comprising the selected tendon; and iii) cloud stored tendon image data;
acquiring, at the computing device, the new ultrasound imaging data;
processing, using the AI model, the new ultrasound imaging data to generate a degree of probability for each of the plurality of different types of tendons that the type of tendon is imaged in the new ultrasound imaging data;
using the at least one user input to corroborate the generated degree of probability for a tendon type of the plurality of different types of tendons; and
based on the corroboration, determining that the tendon type of the plurality of different types of tendons is imaged in the new ultrasound imaging data, hereinafter, the corroborated tendon type.