US 11,836,831 B2
Method for generating an image of an object from measurement data
Yannick Berker, Bensheim (DE); and Marc Kachelrieß, Nuremberg (DE)
Assigned to Deutsches Krebsforschungszentrum, Heidelberg (DE)
Filed by Deutsches Krebsforschungszentrum, Heidelberg (DE)
Filed on Jan. 29, 2021, as Appl. No. 17/162,958.
Application 17/162,958 is a continuation of application No. PCT/EP2019/070360, filed on Jul. 29, 2019.
Claims priority of application No. 18186298 (EP), filed on Jul. 30, 2018.
Prior Publication US 2021/0183117 A1, Jun. 17, 2021
Int. Cl. G06T 11/00 (2006.01); A61B 6/03 (2006.01); A61B 6/00 (2006.01)
CPC G06T 11/005 (2013.01) [A61B 6/032 (2013.01); A61B 6/037 (2013.01); A61B 6/5205 (2013.01); A61B 6/5282 (2013.01); G06T 11/006 (2013.01); G06T 2211/408 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for training of a process for generating an image of an object from measurement data that is obtained with an imaging modality using ionizing radiation, and the measurement data is modified by scatter radiation, the method comprising:
a) providing at least two individual sets of measured data, each set comprising a matrix having matrix elements, each matrix element corresponding to at least one individual detector element configured for detecting ionizing radiation, wherein a signal measured by the individual detector element in an energy bin is assigned as a value for each matrix element, wherein the individual sets of the measured data differ with respect to each other by their corresponding energy bin;
b) using the at least two individual sets of measured data and a template image as an input to a procedure for determining a correction image for correcting a modification of the measured data by the scatter radiation, whereby the process is trained by adjusting a preliminary image obtained by using the at least two individual sets of measured data to the template image, wherein the procedure comprises taking into account a neighborhood of each matrix element; and
c) repeating steps a) and b) until a deviation between the preliminary image obtained by the process and the template image is below a threshold, whereby the procedure for determining the correction image can be implemented in generating the image of the object from the measurement data.