US 12,433,560 B2
Artifact-driven data synthesis in computed tomography
Masaki Ikuta, Pleasanton, CA (US); Junpyo Hong, San Ramon, CA (US); Rajesh Kumar Tamada, Bangalore (IN); and Ravi Soni, San Ramon, CA (US)
Assigned to GE Precision Healthcare LLC, Waukesha, WI (US)
Filed by GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed on Sep. 30, 2022, as Appl. No. 17/937,152.
Prior Publication US 2024/0108299 A1, Apr. 4, 2024
Int. Cl. A61B 6/00 (2024.01); G06T 7/00 (2017.01)
CPC A61B 6/5258 (2013.01) [A61B 6/5235 (2013.01); G06T 7/0012 (2013.01); G06T 2207/10081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer-executable components; and
a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
a simulation component that generates synthetic artifact data corresponding to different computed tomography image artifacts, wherein the different computed tomography image artifacts comprise one or more metal object artifacts and one or more noise artifacts, wherein the simulation component generates the synthetic artifact data using an anatomy agnostic simulation model, and wherein the synthetic artifact data comprises synthetic representations of the different computed tomography image artifacts simulated within a simulation material selected from the group consisting of: a water material, a fat material, a soft tissue material, and a blood material; and
a data augmentation component that combines the synthetic representations with computed tomography images to generate different augmented computed tomography images respectively depicting one or more of the different computed tomography image artifacts.