US 12,446,966 B2
Systems and methods for assisting and augmenting surgical procedures
Jeffrey Roh, Seattle, WA (US); and Justin Esterberg, Mercer Island, WA (US)
Assigned to Carlsmed, Inc., Carlsbad, CA (US)
Filed by Carlsmed, Inc., Carlsbad, CA (US)
Filed on Mar. 17, 2025, as Appl. No. 19/082,041.
Application 19/082,041 is a continuation of application No. 17/497,546, filed on Oct. 8, 2021, granted, now 12,274,506.
Application 17/497,546 is a continuation of application No. 16/048,167, filed on Jul. 27, 2018, granted, now 11,166,764, issued on Nov. 9, 2021.
Claims priority of provisional application 62/537,869, filed on Jul. 27, 2017.
Prior Publication US 2025/0213309 A1, Jul. 3, 2025
Int. Cl. A61B 34/10 (2016.01); A61B 5/00 (2006.01); A61B 34/00 (2016.01); A61B 34/20 (2016.01); A61B 90/00 (2016.01); G06N 5/01 (2023.01); G06N 20/00 (2019.01); G06T 7/73 (2017.01); G06T 19/00 (2011.01); G16H 20/40 (2018.01); G16H 40/63 (2018.01); G16H 50/00 (2018.01)
CPC A61B 34/10 (2016.02) [A61B 5/743 (2013.01); A61B 5/7435 (2013.01); A61B 5/748 (2013.01); A61B 34/20 (2016.02); A61B 34/25 (2016.02); A61B 90/37 (2016.02); G06N 20/00 (2019.01); G06T 7/73 (2017.01); G06T 19/006 (2013.01); G16H 20/40 (2018.01); G16H 40/63 (2018.01); G16H 50/00 (2018.01); A61B 2034/102 (2016.02); A61B 2034/105 (2016.02); A61B 2034/107 (2016.02); A61B 2034/108 (2016.02); A61B 2034/256 (2016.02); A61B 2090/365 (2016.02); G06N 5/01 (2023.01); G06T 2207/10072 (2013.01); G06T 2207/10116 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30012 (2013.01)] 33 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing surgical assistance, the method comprising:
receiving one or more pre-operative images of a patient;
generating at least one virtual model of a spine of the patient based on the one or more pre-operative images;
using at least one trained machine learning model to
determine an acceptable outcome for the patient based on at least one of
the one or more pre-operative images, or
the at least one virtual model, and
design a patient-specific implant to achieve the acceptable outcome for the patient when a virtual implant model the patient-specific implant is virtually implanted along the at least one virtual model of the spine of the patient;
after the patient-specific implant is implanted in the patient, receiving one or more post-operative images of the patient,
comparing the received one or more post-operative images with the acceptable outcome for the patient, and
wherein the at least one trained machine learning model is retrained based on the comparison; and
using the retrained at least one trained machine learning model to design at least one patient-specific implant for another patient.