US 11,980,456 B2
Determining a patient movement during a medical imaging measurement
Rainer Kirsch, Baiersdorf (DE)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Jun. 26, 2020, as Appl. No. 16/912,898.
Claims priority of application No. 19182647 (EP), filed on Jun. 26, 2019.
Prior Publication US 2020/0405179 A1, Dec. 31, 2020
Int. Cl. A61B 5/055 (2006.01); A61B 5/00 (2006.01); A61B 90/00 (2016.01); G06N 20/00 (2019.01)
CPC A61B 5/055 (2013.01) [A61B 5/004 (2013.01); A61B 90/39 (2016.02); G06N 20/00 (2019.01); A61B 2090/3954 (2016.02)] 18 Claims
OG exemplary drawing
 
1. A method for determining a patient movement during a medical imaging measurement with an imaging apparatus, the method comprising:
acquiring reference image data of a body region of a patient;
acquiring patient image data of a part of the body region of the patient during the medical imaging measurement;
providing geometric data for a module of the imaging apparatus, wherein the module partially covers the body region of the patient during the acquisition of the patient image data;
determining, by a processor, adjustment data using the geometric data as a mask, determining the adjustment data comprising producing the adjustment data from the patient image data, producing the adjustment data from the patient image data comprising generating differential data from the geometric data for the module of the imaging apparatus and the patient image data, generating the differential data from the geometric data for the module of the imaging apparatus and the patient image data comprising applying a function trained by machine learning to the geometric data for the module of the imaging apparatus and the patient image data;
determining, by the processor, the patient movement based on the reference image data and the differential data; and
reconstructing one or more images of the patient based on the acquired patient image data and the determined patient movement,
wherein the function is trained by machine learning based on training module image data of the module.