US 11,704,798 B2
Method and device for vertebra localization and identification
Shun Miao, Bethesda, MD (US); Fakai Wang, Bethesda, MD (US); Kang Zheng, Bethesda, MD (US); and Le Lu, Bethesda, MD (US)
Assigned to PING AN TECHNOLOGY (SHENZHEN) CO., LTD., Shenzhen (CN)
Filed by Ping An Technology (Shenzhen) Co., Ltd., Shenzhen (CN)
Filed on Mar. 25, 2021, as Appl. No. 17/212,428.
Claims priority of provisional application 63/120,693, filed on Dec. 2, 2020.
Prior Publication US 2022/0172350 A1, Jun. 2, 2022
Int. Cl. G06T 7/00 (2017.01); G16H 50/20 (2018.01)
CPC G06T 7/0012 (2013.01) [G16H 50/20 (2018.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30012 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A vertebra localization and identification method, comprising:
receiving one or more images of vertebrae of a spine;
applying a machine learning model on the one or more images to generate three-dimensional (3-D) vertebra activation maps {Gv} of detected vertebra centers;
performing a spine rectification process on the 3-D vertebra activation maps {Gv} to convert each 3-D vertebra activation map Gv into a corresponding one-dimensional (1-D) vertebra activation signal Qv;
performing an anatomically-constrained optimization process on each 1-D vertebra activation signal Qv to localize and identify each vertebra center in the one or more images; and
outputting the one or more images, wherein on each of the one or more outputted images, a location k and an identification vl of each vertebra center are specified, wherein vl∈[1, 26].