US 12,243,335 B2
Systems and methods to label structures of interest in tissue slide images
Jack Zeineh, New York, NY (US); Marcel Prastawa, New York, NY (US); and Gerardo Fernandez, New York, NY (US)
Assigned to Icahn School of Medicine at Mount Sinai, New York, NY (US)
Filed by Icahn School of Medicine at Mount Sinai, New York, NY (US)
Filed on Mar. 27, 2024, as Appl. No. 18/617,762.
Application 18/617,762 is a continuation of application No. 17/605,943, granted, now 11,972,621, previously published as PCT/US2020/028162, filed on Apr. 14, 2020.
Claims priority of provisional application 62/838,243, filed on Apr. 24, 2019.
Prior Publication US 2024/0233418 A1, Jul. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/69 (2022.01); G06T 7/00 (2017.01); G06T 7/194 (2017.01); G06T 7/30 (2017.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01)
CPC G06V 20/698 (2022.01) [G06T 7/0012 (2013.01); G06T 7/194 (2017.01); G06T 7/30 (2017.01); G06V 10/82 (2022.01); G06V 20/70 (2022.01); G06T 2200/24 (2013.01); G06T 2207/30024 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method to label structures in tissue slide images, the computer-implemented method comprising:
generating a plurality of tissue slide images including a first tissue slide image of a first tissue slide stained with a first stain and a second tissue slide image of the first tissue slide stained with a second stain;
performing an image registration process on the plurality of tissue slide images,
wherein the image registration process includes minimizing a mutual information metric between deconvolved hematoxylin channels for first images of slides stained with the first stain and second images of slides stained with the second stain, where the minimizing is performed in two stages:
at a first stage, performing a coarse, low-resolution registration of the deconvolved hematoxylin channels using global rigid and affine transforms; and
at a second stage, performing a high-resolution registration of localized fields using affine and B-spline transforms;
based on the image registration process, identifying one or more candidate regions of interest (ROIs) within the plurality of tissue slide images; and
generating one or more label annotations for structures within the plurality of tissue slide images.