Method and device for processing pathological slide image

Patent metadata

Field	Value
Publication number	US-2026057517-A1
Application number	US-202519374026-A
Country	US
Kind code	A1
Filing date	Oct 30, 2025
Priority date	Mar 18, 2022
Publication date	Feb 26, 2026
Grant date	—

Abstract

A computing device includes at least one memory, and at least one processor configured to generate, based on first analysis on a pathological slide image, first biomarker expression information, generate, based on a user input for updating at least some of results of the first analysis, second biomarker expression information about the pathological slide image, and control a display device to output a report including medical information about at least some regions included in the pathological slide image, based on at least one of the first biomarker expression information or the second biomarker expression information.

First claim

What is claimed is:

1 . A computing device comprising:
at least one memory; and at least one processor; wherein the at least one processor configured to: perform a verification of a plurality of pathological slide images; perform first analysis on the plurality of pathological slide images using a machine learning model based on a result of the verification; generate first biomarker expression information about the pathological slide images based on the first analysis; determine priorities of the pathological slide images based on the first biomarker expression information; and control a display device to output the pathological slide images based on the priorities.

2 . The computing device of claim 1 , wherein the verification comprises at least one of first verification on a staining method corresponding to the pathological slide images, second verification on metadata corresponding to the pathological slide images, or third verification on an image pyramid corresponding to the pathological slide images.

3 . The computing device of claim 1 , wherein at least one processor is further configured to perform anonymization on at least one pathological slide image which has passed verification by deleting or masking subject-identifiable information from the at least one pathological slide image.

4 . The computing device of claim 1 , wherein the at least one processor is further configured to generate an alarm notifying an user that the verification on at least one pathological slide image has failed.

5 . The computing device of claim 1 , wherein the at least one processor is configured to:
identify stain expression levels of cells in a pathological slide image of the pathological slide images; calculate a biomarker expression score based on the identified stain expression levels; and determine a high priority of the pathological slide image based on the biomarker expression score.

6 . The computing device of claim 1 , wherein the at least one processor is configured to:
perform second analysis on a pathological slide image based on a user input for updating at least some of results of the first analysis; generate second biomarker expression information based on the second analysis; and control the display device to output at least one of result of the second analysis or the second biomarker expression information.

7 . The computing device of claim 6 , wherein the second analysis comprises a reanalysis of an entire region of the pathological slide images based on the user input.

8 . The computing device of claim 6 , wherein the second biomarker expression information comprises a second biomarker expression score which is calculated based on cell information updated based on the user input.

9 . The computing device of claim 1 , wherein the at least one processor is configured to:
control the display device to output a result of the first analysis of one of the pathological slide images on which the first analysis was performed, and calculate a biomarker expression score of cells included in a drawn region of interest (ROI) based on a user input for drawing the ROI.

10 . A method comprising:
performing a verification of a plurality of pathological slide images; performing first analysis on the plurality of pathological slide images using a machine learning model based on a result of the verification; generating first biomarker expression information about the pathological slide images based on the first analysis; determining priorities of the pathological slide images based on the first biomarker expression information; and outputting the pathological slide images based on the priorities.

11 . The method of claim 10 , wherein the verification comprises at least one of first verification on a staining method corresponding to the pathological slide images, second verification on metadata corresponding to the pathological slide images, or third verification on an image pyramid corresponding to the pathological slide images.

12 . The method of claim 10 further comprising,
performing anonymization on at least one pathological slide image which has passed verification by deleting or masking subject-identifiable information from the at least one pathological slide image.

13 . The method of claim 10 further comprising,
generating an alarm notifying an user that the verification on at least one pathological slide image has failed.

14 . The method of claim 10 ,
wherein the performing first analysis comprises: identifying stain expression levels of cells in a pathological slide image of the pathological slide images; and calculating a biomarker expression score based on the identified stain expression levels, wherein the determining the priorities comprises determining a high priority of the pathological slide image based on the biomarker expression score.

15 . The method of claim 10 further comprising,
performing second analysis on a pathological slide image based on a user input for updating at least some of results of the first analysis;
generating second biomarker expression information based on the second analysis; and
controlling a display device to output at least one of result of the second analysis or the second biomarker expression information.

16 . The method of claim 15 , wherein the second analysis comprises a reanalysis of an entire region of the pathological slide images based on the user input.

17 . The method of claim 15 , wherein the second biomarker expression information comprises a second biomarker expression score which is calculated based on cell information updated based on the user input.

18 . The method of claim 10 , further comprising,
controlling a display device to output a result of the first analysis of one of the pathological slide images on which the first analysis was performed; and calculating biomarker expression score of cells included in a drawn region of interest (ROI) based on a user input for drawing the ROI.

19 . A non-transitory computer-readable recording medium recording thereon a program for executing the method of claim 10 on a computer.

Assignees

• Lunit Inc

Inventors

• Kang Jeong Seok
• Yoo Dong Geun
• Cho Soo Ick
• Jung Won Kyung

Classifications

• G06T2207/30024

  Cell structures in vitro; Tissue sections in vitro · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06F3/14

  Digital output to display device {; Cooperation and interconnection of the display device with other functional units} · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title