US 12,070,349 B2
System and method for targeted object enhancement to generate synthetic breast tissue images
Haili Chui, Fremont, CA (US); Liyang Wei, San Jose, CA (US); Jun Ge, Cupertino, CA (US); and Nikolaos Gkanatsios, Danbury, CT (US)
Assigned to Hologic, Inc., Marlborough, MA (US)
Filed by Hologic, Inc., Marlborough, MA (US)
Filed on Jun. 23, 2022, as Appl. No. 17/847,720.
Application 17/847,720 is a continuation of application No. 16/497,767, granted, now 11,445,993, previously published as PCT/US2018/024913, filed on Mar. 28, 2018.
Claims priority of provisional application 62/479,036, filed on Mar. 30, 2017.
Prior Publication US 2023/0082494 A1, Mar. 16, 2023
Int. Cl. G06K 9/00 (2022.01); A61B 6/00 (2006.01); A61B 6/46 (2024.01); A61B 6/50 (2024.01); G03G 13/054 (2006.01); G06T 5/00 (2006.01); G06T 5/50 (2006.01); G06T 7/00 (2017.01); A61B 6/02 (2006.01)
CPC A61B 6/5217 (2013.01) [A61B 6/463 (2013.01); A61B 6/469 (2013.01); A61B 6/502 (2013.01); A61B 6/5205 (2013.01); A61B 6/5235 (2013.01); G06T 5/00 (2013.01); G06T 5/50 (2013.01); G06T 7/0012 (2013.01); A61B 6/025 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10112 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30068 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for processing breast tissue image data, comprising:
processing image data of a patient's breast tissue to generate a set of image slices that collectively depict the patient's breast tissue, wherein at least two image slices in the set of image slices comprise at least a first object of a first object type and a second object of a second object type;
recognizing, based on a first object recognition process, the first object of the first type;
assigning, based on one or more characteristics of the first object recognition process, a first weight to the first object;
recognizing, based on a second object recognition process, the second object of the second type;
assigning, based on one or more characteristics of the first and second object recognition process, a second weight to the second object, wherein the second weight is greater than the first weight;
populating the first object and the second object to a high-dimensional grid;
determining, based on populating the first object and the second object to a high-dimensional grid, that the first object and the second object overlap;
generating a synthesized image of the patient's breast tissue wherein the second object is emphasized relative to the first object; and
displaying the synthesized image.