Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020088288 - ENDOSCOPIC IMAGE PROCESSING METHOD AND SYSTEM AND COMPUTER DEVICE

Publication Number WO/2020/088288
Publication Date 07.05.2020
International Application No. PCT/CN2019/112202
International Filing Date 21.10.2019
IPC
G06T 7/00 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06T 2207/10068
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10068Endoscopic image
G06T 2207/20081
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20081Training; Learning
G06T 2207/30004
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
30Subject of image; Context of image processing
30004Biomedical image processing
G06T 7/0012
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
0002Inspection of images, e.g. flaw detection
0012Biomedical image inspection
Applicants
  • 腾讯科技(深圳)有限公司 TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED [CN]/[CN]
Inventors
  • 付星辉 FU, Xinghui
  • 孙钟前 SUN, Zhongqian
  • 杨巍 YANG, Wei
Agents
  • 北京三高永信知识产权代理有限责任公司 BEIJING SAN GAO YONG XIN INTELLECTUAL PROPERTY AGENCY CO., LTD.
Priority Data
201811276885.230.10.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) ENDOSCOPIC IMAGE PROCESSING METHOD AND SYSTEM AND COMPUTER DEVICE
(FR) PROCÉDÉ ET SYSTÈME DE TRAITEMENT D’IMAGE ENDOSCOPIQUE ET DISPOSITIF INFORMATIQUE
(ZH) 内窥镜图像的处理方法、系统及计算机设备
Abstract
(EN)
The present application discloses an endoscopic image processing method and system and a computer device. The method comprises: obtaining a current endoscopic image of a user to be examined; using a deep convolutional neural network to perform a prediction with respect to the current endoscopic image on the basis of a training parameter, the training parameter being determined on the basis of at least one first endoscopic image and at least one second endoscopic image being converted from the at least one first endoscopic image, the endoscopic images corresponding to a body part; and determining an organ type corresponding to the current endoscopic image. The method proposed in the present invention provides a more intelligent prediction process and improved robustness, and increases resource utilization of a processing device.
(FR)
La présente invention concerne un procédé et un système de traitement d'image endoscopique et un dispositif informatique. Le procédé consiste : à obtenir une image endoscopique actuelle d'un utilisateur à examiner ; à utiliser un réseau neuronal à convolution profonde pour effectuer une prédiction par rapport à l'image endoscopique actuelle sur la base d'un paramètre d'apprentissage, le paramètre d'apprentissage étant déterminé sur la base d'au moins une première image endoscopique et au moins une seconde image endoscopique étant convertie à partir de ladite image endoscopique, les images endoscopiques correspondant à une partie du corps ; et à déterminer un type d'organe correspondant à l'image endoscopique actuelle. Le procédé proposé dans la présente invention fournit un processus de prédiction plus intelligent et une robustesse améliorée, et augmente l'utilisation des ressources d'un dispositif de traitement.
(ZH)
本申请公开了一种内窥镜图像的处理方法、系统及计算机设备。该方法包括:获取待检用户的当前内窥镜图像;使用深度卷积网络基于训练参数对当前内窥镜图像进行预测,该训练参数根据至少一个第一内窥镜图像和对至少一个第一内窥镜图像进行变换后的至少一个第二内窥镜图像而确定,该至少一个内窥镜图像对应于人体部位;确定出当前内窥镜图像所对应的器官类别。本发明的这种方法,使得预测过程更加智能化,鲁棒性更强,提高了处理装置的资源利用率。
Also published as
Latest bibliographic data on file with the International Bureau