US 12,254,534 B2
Movement-compensated image reconstruction for an x-ray based imaging method
Michael Manhart, Fürth (DE); Alexander Preuhs, Erlangen (DE); and Manuela Meier, Nuremberg (DE)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthineers AG, Forchheim (DE)
Filed on Jan. 12, 2024, as Appl. No. 18/411,393.
Claims priority of application No. 23151982 (EP), filed on Jan. 17, 2023.
Prior Publication US 2024/0242397 A1, Jul. 18, 2024
Int. Cl. G06T 11/00 (2006.01); G06T 7/285 (2017.01)
CPC G06T 11/003 (2013.01) [G06T 7/285 (2017.01); G06T 2207/10081 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for creation of a movement-compensated image reconstruction for an x-ray based imaging method, the method comprising:
providing a plurality of projection images of an object using the x-ray based imaging method;
providing a trained algorithm that is trained to allocate an object movement trajectory to a latent vector of a latent space;
determining an optimal object movement trajectory by application of the trained algorithm to an optimal latent vector and wherein the movement-compensated image reconstruction is created depending on the plurality of projection images, wherein the object has moved in accordance with the optimal object movement trajectory while the x-ray based imaging method was carried out; and
determining the optimal latent vector by a cost function being minimized using the latent vector as an optimization parameter,
determining, for each optimization step with a current latent vector, a current object movement trajectory by application of the trained algorithm to the current latent vector; and
computing a current value of the cost function depending on the plurality of projection images, wherein the object has moved in accordance with the current object movement trajectory while the x-ray based imaging method was being carried out.