Title:
DISEASE DIAGNOSIS SYSTEM AND METHOD FOR PERFORMING SEGMENTATION BY USING NEURAL NETWORK AND UNLOCALIZED BLOCK
Document Type and Number:
WIPO Patent Application WO/2021/010671
Kind Code:
A9
Abstract:
Disclosed are a disease diagnosis system and method, which learn through a neural network so as to use a trained neural network and an unlocalized block, thereby enabling segmentation of a diseased area in an image of a biological tissue. According to one aspect of the present invention, provided is a disease diagnosis system, which is implemented in a system comprising a processor and a storage device storing a neural network and uses a slide of a biological image and the neural network, the disease diagnosis system comprising a patch level segmentation neural network which receives, for each predetermined patch in which the slide is divided into a predetermined size, the patch as an input layer so as to specify the area in which the disease in the patch exists, wherein the patch level segmentation neural network comprises: a patch level classification neural network, which receives the patch as an input layer so as to output a patch level classification result about whether the disease exists in the patch; and a patch level segmentation architecture, which receives a feature map generated in each of two or more feature map extraction layers from among hidden layers included in the patch level classification neural network, so as to specify the area in which the disease in the patch exists.
Inventors:
KIM SUN WOO (KR)
CHO JOON YOUNG (KR)
LEE SANG HUN (KR)
CHO JOON YOUNG (KR)
LEE SANG HUN (KR)
Application Number:
PCT/KR2020/009096
Publication Date:
May 27, 2021
Filing Date:
July 10, 2020
Export Citation:
Assignee:
DEEP BIO INC (KR)
International Classes:
G16H50/20; G06N3/08; G06N20/00; G16H30/40; G16H70/60
Attorney, Agent or Firm:
SHIM, Choong Sup (KR)
Download PDF: