US 11,748,981 B2
Deep learning method for predicting patient response to a therapy
Guenter Schmidt, Munich (DE); Nicolas Brieu, Munich (DE); Ansh Kapil, Munich (DE); and Jan Martin Lesniak, Munich (DE)
Assigned to AstraZeneca Computational Pathology GmbH, Munich (DE)
Filed by AstraZeneca Computational Pathology GmbH, Munich (DE)
Filed on Apr. 27, 2022, as Appl. No. 17/731,228.
Application 17/731,228 is a continuation of application No. 16/705,238, filed on Dec. 6, 2019, granted, now 11,348,231.
Claims priority of provisional application 62/776,443, filed on Dec. 6, 2018.
Prior Publication US 2022/0254020 A1, Aug. 11, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/82 (2022.01); G06T 7/00 (2017.01); G06V 20/69 (2022.01); G06V 10/764 (2022.01); G06T 7/136 (2017.01); G06T 7/33 (2017.01); G06T 7/35 (2017.01); G01N 1/30 (2006.01); G06F 18/2413 (2023.01)
CPC G06V 10/82 (2022.01) [G01N 1/30 (2013.01); G06F 18/2414 (2023.01); G06T 7/0012 (2013.01); G06T 7/136 (2017.01); G06T 7/337 (2017.01); G06T 7/35 (2017.01); G06V 10/764 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G01N 2800/52 (2013.01); G01N 2800/7028 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30242 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
detecting cell centers on a digital image of tissue of a cancer patient, wherein the tissue has been stained;
for each cell center, extracting an image patch that includes the cell center;
generating a feature vector based on each image patch using a convolutional neural network;
assigning a class to each cell center based on the feature vector associated with each image patch that includes the cell center; and
computing a score for the digital image of tissue based on how the cell centers assigned to each of the classes of cell centers are spatially distributed in the digital image and based on how many cell centers assigned to a first class are located closer than a predetermined distance to a predetermined number of cell centers assigned to a second class, wherein the score is indicative of how the cancer patient will respond to a predetermined therapy.