Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text and picture-based bimodal stomach disease classification method and device

A dual-modal, text-based technology, applied in neural learning methods, character and pattern recognition, computer components, etc., can solve problems such as low efficiency of manual diagnosis of gastric diseases

Pending Publication Date: 2021-05-11
紫东信息科技(苏州)有限公司
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a dual-mode gastric disease classification method and device based on text and pictures, which can solve the problem of low efficiency of manual diagnosis of gastric diseases

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Text and picture-based bimodal stomach disease classification method and device
  • Text and picture-based bimodal stomach disease classification method and device
  • Text and picture-based bimodal stomach disease classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0037] First, some terms involved in this application are introduced.

[0038] Bidirectional Encoder Representations from Transformers (Bidirectional Encoder Representations from Transformers, BERT): It is a large-scale unsupervised pre-training language model. As a substitute for Word2vec, it refreshes the accuracy in the field of Natural Language Processing (NLP). One of the most groundbreaking techniques from residual networks in recent years. The essence of BERT is to learn a good feature representation for words by running a self-supervised learning method on the basis of massive corpus, and it provides a transferable model for other tasks. Its advantage is that it integrates the Trans...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a bimodal stomach disease classification method and device based on texts and pictures, and belongs to the technical field of medical text and image bimodal intelligent process. The method comprises the following steps: inputting a medical record report into a pre-trained text extraction network to obtain a text feature vector of the medical record report; inputting the gastroscope picture into a pre-trained picture extraction network to obtain a picture feature vector of the gastroscope picture; and performing feature fusion on the text feature vector and the picture feature vector, and inputting the fused feature vector into a pre-trained classifier to obtain a classification result of the stomach disease. The problem that the efficiency of manual stomach disease diagnosis is low can be solved. The stomach diseases are automatically classified, and the stomach disease diagnosis effect is improved. Besides, stomach disease classification is carried out by combining the text feature vector and the picture feature vector, and compared with independent use of texts or pictures, the classification accuracy is higher.

Description

【Technical field】 [0001] The present application relates to a dual-mode gastric disease classification method and device based on text and pictures, and belongs to the technical field of dual-mode intelligent processing of medical text and images. 【Background technique】 [0002] Gastric cancer is a malignant tumor originating from the gastric mucosal epithelium, and its incidence ranks first among all kinds of malignant tumors in my country. Due to the remarkable effect of gastroscopy in the diagnosis of gastric cancer, it has been recommended as the main diagnostic method for gastric cancer. [0003] Specifically, gastroscopy can directly detect the lesion tissue area in the stomach to make a corresponding diagnosis. Under gastroscopy, tissue biopsy can be performed for the diagnosis of early gastric cancer precancerous diseases or precancerous lesions and the identification of benign and malignant ulcers. effect. [0004] However, due to human factors such as inconsisten...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/08G06N3/04
CPCG06N3/08G06V30/40G06V2201/03G06N3/045G06F18/24G06F18/253G06F18/214
Inventor 李寿山罗佳敏王晶晶周国栋张民
Owner 紫东信息科技(苏州)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com