The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 25, 2021

Filed:

Dec. 26, 2019
Applicant:

Tienovix, Llc, Houston, TX (US);

Inventors:

William R. Buras, Friendswood, TX (US);

Craig S. Russell, League City, TX (US);

Kyle Q. Nguyen, League City, TX (US);

Assignee:

Tienovix, LLC, Houston, TX (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G09B 23/28 (2006.01); G06N 20/00 (2019.01); A61B 34/20 (2016.01); G16H 40/63 (2018.01); A61B 8/06 (2006.01); A61B 8/08 (2006.01); A61B 8/00 (2006.01); A61B 90/00 (2016.01); G16H 30/20 (2018.01); G06F 3/01 (2006.01); G09B 5/06 (2006.01); G02B 27/01 (2006.01);
U.S. Cl.
CPC ...
G09B 23/286 (2013.01); A61B 8/06 (2013.01); A61B 8/085 (2013.01); A61B 8/4245 (2013.01); A61B 8/4254 (2013.01); A61B 8/4263 (2013.01); A61B 8/466 (2013.01); A61B 8/467 (2013.01); A61B 8/52 (2013.01); A61B 34/20 (2016.02); A61B 90/361 (2016.02); G06F 3/011 (2013.01); G06F 3/016 (2013.01); G06N 20/00 (2019.01); G09B 5/065 (2013.01); G16H 30/20 (2018.01); G16H 40/63 (2018.01); A61B 2034/2048 (2016.02); A61B 2034/2055 (2016.02); A61B 2090/365 (2016.02); A61B 2090/378 (2016.02); A61B 2090/3945 (2016.02); A61B 2562/0219 (2013.01); G02B 27/017 (2013.01);
Abstract

Methods for developing a machine learning model of a neural network for classifying medical images using a medical imaging system such as an ultrasound system. The methods involve capturing images during a first medical procedure, analyzing the images for the presence of one or more features, labeling the images as belonging to one or more classes, splitting the labeled images into a training set and a validation set. Training and validation processes are then performed, and the machine learning model may be used when training process metrics and validation process metrics for the training and validation processes are within acceptable thresholds.


Find Patent Forward Citations

Loading…