Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LYMPH NODE METASTASIS PREDICTION METHOD USING ENDOSCOPIC RESECTION SAMPLE IMAGE OF EARLY COLON CANCER, AND ANALYSIS DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/260380
Kind Code:
A1
Abstract:
A lymph node metastasis prediction method using an endoscopic resection sample image of early colon cancer, comprises steps in which: an analysis device receives a stained sample image of the colon area of a patient with colon cancer; the analysis device inputs the sample image into a deep learning model trained in advance; and the analysis device predicts, on the basis of a value output by the deep learning model having received the sample image, whether lymph node metastasis has occurred in the patient with colon cancer. The deep learning model receives patch images in which the whole sample image is divided into a plurality of areas, and outputs, on the basis of the feature about the whole sample image to which weights for the patch images are provided, a prediction value about whether lymph node metastasis has occurred in the patient.

Inventors:
KIM EUN RAN (KR)
SONG JOO HYE (KR)
KIM SEOK HYUNG (KR)
HONG YI YU (KR)
SOHN INSUK (KR)
Application Number:
PCT/KR2022/007967
Publication Date:
December 15, 2022
Filing Date:
June 07, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG LIFE PUBLIC WELFARE FOUNDATION (KR)
ARONTIER CO LTD (KR)
International Classes:
G16H50/50; A61B5/00; G06T7/11; G16H30/20; G16H30/40
Foreign References:
US20190156476A12019-05-23
KR20200087427A2020-07-21
US20190206055A12019-07-04
KR101919866B12018-11-19
JP2007037421A2007-02-15
Attorney, Agent or Firm:
ISIS IP LAW LLC (KR)
Download PDF: