US 11,996,197 B2
Generating modified medical images and detecting abnormal structures
Sebastian Guendel, Erlangen (DE); Arnaud Arindra Adiyoso, Nuremberg (DE); Sasa Grbic, Plainsboro, NJ (US); and Dorin Comaniciu, Princeton Junction, NJ (US)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Mar. 4, 2021, as Appl. No. 17/191,943.
Claims priority of provisional application 62/988,429, filed on Mar. 12, 2020.
Claims priority of application No. 10 2020 212 113.3 (DE), filed on Sep. 25, 2020.
Prior Publication US 2021/0287799 A1, Sep. 16, 2021
Int. Cl. G16H 50/00 (2018.01); G06T 7/11 (2017.01); G06T 7/33 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)
CPC G16H 50/20 (2018.01) [G06T 7/11 (2017.01); G06T 7/337 (2017.01); G16H 30/40 (2018.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/10108 (2013.01); G06T 2207/10116 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20028 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30064 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving a first medical image, the first medical image displaying an abnormal structure within a patient;
applying a trained inpainting function to the first medical image, to generate a modified first medical image, the trained inpainting function being trained to inpaint abnormal structures within a medical image;
determining an abnormality patch based on the first medical image and the modified first medical image;
receiving a second medical image, the second medical image being of a same type as the first medical image; and
generating a modified second medical image by including the abnormality patch in the second medical image.