US 11,883,220 B2
Technologies for determining the spatial orientation of input imagery for use in an orthopaedic surgical procedure
Shawnoah S. Pollock, South Bend, IN (US); and R. Patrick Courtis, Boston, MA (US)
Assigned to DePuy Synthes Products, Inc., Raynham, MA (US)
Filed by DePuy Synthes Products, Inc., Raynham, MA (US)
Filed on Oct. 4, 2021, as Appl. No. 17/493,003.
Application 17/493,003 is a continuation of application No. 16/586,887, filed on Sep. 27, 2019, granted, now 11,134,908.
Prior Publication US 2022/0022831 A1, Jan. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 6/00 (2006.01); G06K 9/00 (2022.01); A61B 34/10 (2016.01); G06T 7/00 (2017.01); G06T 11/00 (2006.01)
CPC A61B 6/488 (2013.01) [A61B 6/505 (2013.01); A61B 6/583 (2013.01); A61B 34/10 (2016.02); G06T 7/0012 (2013.01); A61B 6/547 (2013.01); A61B 2034/105 (2016.02); G06T 11/00 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer comprising:
circuitry configured to:
determine first candidate values indicative of an orientation of an anatomical object in each of a plurality of two-dimensional images showing a plurality of bones of a human joint;
produce, as a function of the plurality of two-dimensional images and the candidate values, a first candidate three-dimensional model of the anatomical object;
determine a first score indicative of an accuracy of the first candidate three-dimensional model;
determine, in response to the first score not satisfying a threshold, second candidate values indicative of the orientation of the anatomical object in each of the plurality of two-dimensional images;
produce, as a function of the plurality of two-dimensional images and the second candidate values, a second candidate three-dimensional model of the anatomical object;
determine a second score indicative of an accuracy of the second candidate three-dimensional model;
determine, in response to the second score not satisfying the threshold, third candidate values indicative of the orientation of the anatomical object in each of the plurality of two-dimensional images; and
produce, as a function of the plurality of two-dimensional images and the third candidate values, a third candidate three-dimensional model of the anatomical object.