US 12,031,988 B2
Distance-based tissue state determination
Fabien Gaire, Penzberg (DE); Karin Emilia Andersson, Penzberg (DE); Franziska Braun, Penzberg (DE); Konstanty Korski, Penzberg (DE); and Fabian Schmich, Penzberg (DE)
Assigned to Hoffmann-La Roche, Inc., Little Falls, NJ (US)
Appl. No. 17/284,610
Filed by HOFFMANN-LA ROCHE INC., Little Falls, NJ (US)
PCT Filed Oct. 23, 2019, PCT No. PCT/EP2019/078819
§ 371(c)(1), (2) Date Apr. 12, 2021,
PCT Pub. No. WO2020/083970, PCT Pub. Date Apr. 30, 2020.
Claims priority of application No. 18202125 (EP), filed on Oct. 23, 2018.
Prior Publication US 2021/0343009 A1, Nov. 4, 2021
Int. Cl. G01N 33/574 (2006.01); G06T 7/00 (2017.01)
CPC G01N 33/574 (2013.01) [G06T 7/0012 (2013.01); G06T 2207/30024 (2013.01)] 21 Claims
OG exemplary drawing
 
1. An image analysis method for determining the biomedical state of a tissue sample, the method being implemented by an image analysis system and comprising:
receiving a digital image of a tissue sample;
analyzing the received image for identifying the number and location of A-type cells and B-type cells observed in an area of the received image, wherein the A-type and the B-type are different cell types;
analyzing the location of the A-type and B-type cells in the area for obtaining an observed relative distribution, the observed relative distribution being indicative of observed distances between the A-type cells and the B-type cells in the area;
obtaining a reference relative distribution, the reference relative distribution being indicative of expected distances between reference A-type cells and reference B-type cells, wherein the expected distances are the distances that are expected assuming that the A-type cells and/or the B-type cells are distributed in the image area in accordance with a particular predefined mathematical distribution;
computing a proximity score as a difference of the reference relative distribution and the observed relative distribution;
computing a combined score, the combined score comprising the proximity score and comprising the density of the A-type cells and/or the density of the B-type cells;
using the combined score for determining the biomedical state of the tissue sample and/or outputting the combined score to a user for enabling the user to determine the biomedical state of the tissue sample.