US 12,256,996 B2
Systems and methods for generating a three-dimensional model of a joint from two-dimensional images
Brian Fouts, Morgan Hill, CA (US); Jakob Kemper, Heemstede (NL); Heiko Michael Gottschling, Munich (DE); and Manuel Schroeder, Ellingen (DE)
Assigned to Stryker Corporation, Portage, MI (US)
Filed by Stryker Corporation, Kalamazoo, MI (US)
Filed on Dec. 14, 2021, as Appl. No. 17/644,335.
Claims priority of provisional application 63/125,932, filed on Dec. 15, 2020.
Prior Publication US 2022/0183760 A1, Jun. 16, 2022
Int. Cl. A61B 34/10 (2016.01); A61B 90/00 (2016.01); G06T 7/00 (2017.01); G06T 7/32 (2017.01)
CPC A61B 34/10 (2016.02) [A61B 90/37 (2016.02); G06T 7/0012 (2013.01); G06T 7/32 (2017.01); A61B 2034/105 (2016.02); A61B 2090/374 (2016.02); A61B 2090/3764 (2016.02); G06T 2207/10028 (2013.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/10121 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30008 (2013.01)] 29 Claims
OG exemplary drawing
 
1. A method for modeling at least a portion of a joint before, during and/or after a medical procedure, the method comprising:
receiving first imaging data capturing the at least a portion of the joint from a first imaging perspective and second imaging data capturing the at least a portion of the joint from a second imaging perspective that is different than the first imaging perspective, the first and second imaging data generated via a two-dimensional imaging modality;
generating three-dimensional image data by back-projecting the first and second imaging data in three-dimensional space in accordance with a relative difference between the first and second imaging perspectives;
generating a three-dimensional model of the at least a portion of the joint by:
generating a set of multi-class voxels by processing the three-dimensional image data with a machine learning model trained on imaging data generated via at least a three-dimensional imaging modality; and
generating the three-dimensional model of the at least a portion of the joint based on multi-class voxels of the set of multi-class voxels that correspond to at least one class associated with the at least a portion of the joint; and
displaying a visualization based on the three-dimensional model of the at least a portion of the joint during the medical procedure.