US 12,033,247 B2
Three-dimensional shape reconstruction from a topogram in medical imaging
Elena Balashova, Princeton, NJ (US); Jiangping Wang, Carteret, NJ (US); Vivek Singh, Princeton, NJ (US); and Bogdan Georgescu, Princeton, NJ (US)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Appl. No. 17/295,631
Filed by Siemens Healthineers AG, Forchheim (DE)
PCT Filed May 31, 2019, PCT No. PCT/EP2019/064161
§ 371(c)(1), (2) Date May 20, 2021,
PCT Pub. No. WO2020/114632, PCT Pub. Date Jun. 11, 2020.
Claims priority of provisional application 62/775,440, filed on Dec. 5, 2018.
Prior Publication US 2022/0028129 A1, Jan. 27, 2022
Int. Cl. G06T 11/00 (2006.01); G06N 20/00 (2019.01)
CPC G06T 11/006 (2013.01) [G06N 20/00 (2019.01); G06T 2210/41 (2013.01); G06T 2211/40 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method for reconstruction of a three-dimensional shape from a patient topogram in a medical imaging system, the method comprising:
acquiring the patient topogram representing a projection through a patient in two dimensions;
reconstructing the three-dimensional shape of an object represented in the patient topogram, the reconstructing being by a machine-learned generative network in response to input of the patient topogram to the machine-learned generative network, wherein the machine-learned generative network comprises:
a mask encoder configured to predict a first latent coordinate of an organ shape given a 2D mask;
a 2D image encoder configured to predict a second latent coordinate given a 2D topogram image;
a combiner configured to map the outputs of the mask encoder and the 2D image encoder to a common latent coordinate;
a 3D shape encoder configured to input a 3D shape, wherein the 3D shape encoder is used as a regularlizer in training of the machine-learned generative network and is not used in application of the machine-learned generative network; and
a shape decoder configured to input the common latent coordinate and output the three-dimensional shape; and
displaying information from the three-dimensional shape.