US 12,336,852 B2
Methods for generating skeletal characteristic values related to bone quality
Chia-Hung Lin, New Taipei (TW); and Win-How Lee, New Taipei (TW)
Assigned to ALPHA INTELLIGENCE MANIFOLDS, INC., New Taipei (TW)
Filed by Alpha Intelligence Manifolds, Inc., New Taipei (TW)
Filed on Jul. 22, 2022, as Appl. No. 17/814,501.
Claims priority of application No. 110127047 (TW), filed on Jul. 22, 2021.
Prior Publication US 2023/0029674 A1, Feb. 2, 2023
Int. Cl. A61B 6/50 (2024.01); A61B 5/00 (2006.01); A61B 6/00 (2006.01); A61B 6/46 (2024.01)
CPC A61B 6/505 (2013.01) [A61B 5/4509 (2013.01); A61B 6/469 (2013.01); A61B 6/5217 (2013.01)] 42 Claims
OG exemplary drawing
 
1. A method of generating one or more skeletal characteristic values (SCVs) of a subject from a planar bone image, comprising the steps of:
identifying one or more regions of interest (ROIs) in the planar bone image; and
performing one or more feature analyses on the regions of interest (ROIs) to generate the skeletal characteristic values (SCVs) comprising a plurality of density SCVs related to bone density;
wherein the planar bone image is a fixed angle projection image;
wherein the planar bone image does not include an image of a phantom with known densities; and
wherein the feature analyses comprise a density analysis performed by a trained machine learning model to generate the plurality of density SCVs from one of the ROIs.