US 12,475,727 B2
Image-processing-based object classification bootstrapping of region-level annotations
Mohamed Amgad Tageldin, Tucson, AZ (US); Lee Alex Donald Cooper, Tucson, AZ (US); Jim F. Martin, Tucson, AZ (US); and Uday Kukure, Tucson, AZ (US)
Assigned to Ventana Medical Systems, Inc., Tucson, AZ (US)
Filed by Ventana Medical Systems, Inc., Tucson, AZ (US)
Filed on Apr. 27, 2022, as Appl. No. 17/730,406.
Application 17/730,406 is a continuation of application No. PCT/US2020/056340, filed on Oct. 19, 2020.
Claims priority of provisional application 62/929,100, filed on Oct. 31, 2019.
Prior Publication US 2022/0262145 A1, Aug. 18, 2022
Int. Cl. G06V 20/69 (2022.01); G06T 7/00 (2017.01); G06V 10/25 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/698 (2022.01) [G06T 7/0014 (2013.01); G06V 10/25 (2022.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/7747 (2022.01); G06V 10/82 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30096 (2013.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
accessing a set of images;
for each image of the set of images:
identifying multiple regions within the image, wherein each region of the multiple regions corresponds to an area of the image in which cells depicted within the area of the image have similar visual characteristics;
for each respective region of the multiple regions:
identifying a region-specific label for the respective region, wherein the region-specific label indicates a particular cell type for cells in an area of the image associated with the respective region;
detecting a set of objects within the respective region; and
assigning, to each respective object of the set of objects, an object-specific label to the respective object, the object-specific label being the same as the region-specific label for the respective region;
defining a training data set to include, for each image of the set of images:
object-location data that indicates, for each object of the set of objects, intra-image location data for the object; and
label data that indicates, for each object of the set of objects, the object-specific label assigned to the object; and
training an image-processing model using the training data, wherein the training includes learning a set of parameter values for a set of parameters that define calculations performed by the image-processing model.