US 11,869,185 B2
Systems and methods for processing images to prepare slides for processed images for digital pathology
Rodrigo Ceballos Lentini, Flemington, NJ (US); Christopher Kanan, Pittsford, NY (US); Patricia Raciti, New York, NY (US); Leo Grady, Darien, CT (US); and Thomas Fuchs, New York, NY (US)
Assigned to Paige.AI, Inc., New York, NY (US)
Filed by PAIGE.AI, Inc., New York, NY (US)
Filed on May 26, 2022, as Appl. No. 17/804,123.
Application 17/804,123 is a continuation of application No. 17/654,614, filed on Mar. 14, 2022, granted, now 11,676,274.
Application 17/654,614 is a continuation of application No. 17/346,923, filed on Jun. 14, 2021, granted, now 11,309,074, issued on Apr. 19, 2022.
Application 17/346,923 is a continuation of application No. 17/137,769, filed on Dec. 30, 2020, granted, now 11,062,801, issued on Jul. 13, 2021.
Application 17/137,769 is a continuation of application No. 16/884,978, filed on May 27, 2020, granted, now 10,937,541, issued on Mar. 2, 2021.
Claims priority of provisional application 62/853,383, filed on May 28, 2019.
Prior Publication US 2022/0293251 A1, Sep. 15, 2022
Int. Cl. G06T 7/00 (2017.01); G16H 50/20 (2018.01); G16H 30/40 (2018.01); G06F 18/214 (2023.01)
CPC G06T 7/0012 (2013.01) [G06F 18/214 (2023.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30096 (2013.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system for processing images, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving an image of a slide comprising a sample of tissue from a patient;
providing the image as an input image to a trained convolutional neural network (CNN) to obtain a segmentation output image from the trained CNN, the segmentation output image assigning a tissue type from a plurality of tissue types to each pixel in the input image, wherein the CNN is trained based on a training data set including a plurality of training images comprising samples of tissue and, for each of the plurality of training images, corresponding segmentation labels of a tissue type from the plurality of tissue types assigned to each pixel of the respective training image;
determining one or more tests are to be performed on the tissue based on at least one tissue type in the segmentation output image; and
automatically ordering the one or more tests.