US 12,396,869 B2
Systems and methods for using image analysis to guide a surgical procedure
Chandra Jonelagadda, San Francisco, CA (US)
Assigned to Kaliber Labs Inc., San Francisco, CA (US)
Filed by Kaliber Labs Inc., San Francisco, CA (US)
Filed on Apr. 16, 2024, as Appl. No. 18/637,440.
Application 18/637,440 is a continuation of application No. 18/555,252, granted, now 12,004,966, previously published as PCT/US2022/024503, filed on Apr. 12, 2022.
Claims priority of provisional application 63/173,943, filed on Apr. 12, 2021.
Prior Publication US 2024/0341980 A1, Oct. 17, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/62 (2017.01); A61B 1/00 (2006.01); A61B 1/317 (2006.01); A61F 2/46 (2006.01); G16H 20/40 (2018.01)
CPC A61F 2/4612 (2013.01) [A61B 1/000096 (2022.02); A61B 1/317 (2013.01); G06T 7/62 (2017.01); G16H 20/40 (2018.01); A61F 2002/4633 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/10068 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30008 (2013.01); G06T 2207/30204 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for guiding a surgical procedure, the method comprising:
receiving imaging data contained in a video stream captured by an in-situ imaging device that traverses a treatment site of a patient;
processing image data from the in-situ imaging device;
analyzing the image data to (i) detect image data that depicts a set of structures in the treatment site, (ii) determine an orientation attribute of each structure of the set with respect to a reference; and (iii) determine a respective scale factor for one or more portions of image data that depict each structure of the set, the respective scale factor of each portion of the image data reflecting a distortion in size of that portion of the image data with respect to a reference scale;
determining geometric information for at least a portion of the treatment site where the set of structures are located; and
calculating at least a first measurement that represents a physical span between a pair of structures of the set, based at least in part on the orientation attribute of each structure of the set, the respective scale factor of each portion of the image data, and the determined geometric information.