US 11,720,647 B2
Synthetic training data generation for improved machine learning model generalizability
Ravi Soni, San Ramon, CA (US); Tao Tan, Eindhoven (NL); Gopal B. Avinash, San Ramon, CA (US); Dibyajyoti Pati, Dublin, CA (US); Hans Krupakar, San Ramon, CA (US); and Venkata Ratnam Saripalli, Danville, CA (US)
Assigned to GE PRECISION HEALTHCARE LLC, Wauwatosa, WI (US)
Filed by GE Precision Healthcare LLC, Milwaukee, WI (US)
Filed on Aug. 21, 2020, as Appl. No. 16/999,665.
Prior Publication US 2022/0058437 A1, Feb. 24, 2022
Int. Cl. G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06F 18/21 (2023.01); G06N 3/08 (2023.01); G06N 20/10 (2019.01); G06V 10/774 (2022.01); G16H 30/40 (2018.01); G06T 11/00 (2006.01)
CPC G06F 18/2148 (2023.01) [G06F 18/214 (2023.01); G06F 18/2163 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06T 11/00 (2013.01); G06V 10/774 (2022.01); G16H 30/40 (2018.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor that executes computer-executable instructions stored in a memory, which causes the processor to:
access an annotated source image;
generate a set of preliminary annotated training images based on the annotated source image, wherein each preliminary annotated training image is formed by inserting a respective permutation of visual objects into the annotated source image, wherein such visual objects include medical equipment or biological symptoms;
generate a set of intermediate annotated training images based on the set of preliminary annotated training images, wherein each intermediate annotated training image is formed by applying a respective permutation of modality characteristic variations to a respective preliminary annotated training image, wherein such modality characteristic variations include changes to image properties that depend upon settings or parameters of a medical imaging device that captured or generated the annotated source image; and
generate a set of deployable annotated training images based on the set of intermediate annotated training images, wherein each deployable annotated training image is formed by applying a respective permutation of geometric variations to a respective intermediate annotated training image, wherein such geometric variations include spatial transformations of image pixel grids.