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:
Oct. 06, 2026

Filed:

Jun. 10, 2025
Applicant:

Digital Surgery Systems, Inc., Goleta, CA (US);

Inventors:

Kyle Kam, San Mateo, CA (US);

Mannat Rana, Phoenix, AZ (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04N 23/68 (2023.01); A61B 34/20 (2016.01); G06T 7/246 (2017.01); G06T 7/277 (2017.01); G06T 7/73 (2017.01); G16H 30/40 (2018.01); A61B 34/10 (2016.01);
U.S. Cl.
CPC ...
A61B 34/20 (2016.02); G06T 7/248 (2017.01); G06T 7/277 (2017.01); G06T 7/74 (2017.01); G16H 30/40 (2018.01); H04N 23/6811 (2023.01); H04N 23/683 (2023.01); A61B 2034/107 (2016.02); A61B 2034/2055 (2016.02); A61B 2034/2065 (2016.02); G06T 2207/10016 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30004 (2013.01); G06T 2207/30241 (2013.01);
Abstract

The present invention relates to surgical image processing and update by a computing device. The method disclosed herein uses a deep learning model to detect distal ends of tools in an image from a microscope and processes the image to output detections that are optionally displayed around the distal ends of the tools. The method disclosed herein also uses Kalman filters and camera motion compensation calculations to process the image and predict the locations and sizes of the bounding boxes around the distal ends of the tools. The two processes work parallelly, with the Kalman filters and camera motion compensation calculations working at a higher rate than the deep learning model, thereby allowing an increased update rate of detections while not significantly increasing computing workload.


Find Patent Forward Citations

Loading…