Mode-driven intelligent gastroscopy report generation method and system

A gastroscopy, mode-driven technology, applied in medical reports, neural learning methods, biological neural network models, etc., can solve the problem of low level of automatic generation of gastroscopy reports, achieve the effect of reducing work pressure and improving the degree of automation

Active Publication Date: 2021-10-26
HEFEI UNIV OF TECH +1
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a mode-driven method, system, storage medium and electronic equipment for intelligently generating gastroscopy reports, which solves the technical problem of low level of automatic generation of gastroscopy reports

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
  • Mode-driven intelligent gastroscopy report generation method and system
  • Mode-driven intelligent gastroscopy report generation method and system
  • Mode-driven intelligent gastroscopy report generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] First aspect, such as Figure 1~2 As shown, the embodiment of the present invention provides a mode-driven gastroscopy report intelligent generation method, including:

[0072] S1. Preprocessing the gastroscopy picture, and obtaining the visual features and part feature vectors of the gastroscopy picture;

[0073] S2. Fusing the visual features and part feature vectors to obtain the overall feature vector of the gastroscopy picture;

[0074] S3. Input the overall feature vector into the encoder of the Transformer model, and obtain the hidden layer state value encoded by the overall feature vector;

[0075] S4. Input the state value of the hidden layer into the decoder of the Transformer model to obtain the target text sequence vector corresponding to the gastroscopy picture, and the decoder introduces a position pattern memory, and the position pattern memory records information related to the position pattern memory. The key pattern information corresponding to the p...

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 provides a mode-driven intelligent gastroscopy report generation method and system, a storage medium and electronic equipment, and relates to the technical field of intelligent gastroscopy report generation. According to the method, gastroscopy images and a pre-constructed report dictionary are fused, a pre-trained image part recognition network is constructed on the basis of an encoder-decoder framework of Transformer, and part feature information of the images is extracted; meanwhile, a gastroscopy position mode storage module LMS is designed; the method accords with a clinical report generation process, and professional knowledge and experience of gastroscope doctors are integrated; by referring to the key mode information of the same examination part report, the automation degree of report generation is effectively improved, and the work pressure of gastroscope doctors for writing examination reports is greatly relieved.

Description

technical field [0001] The invention relates to the technical field of intelligent generation of gastroscopy reports, in particular to a mode-driven intelligent generation method, system, storage medium and electronic equipment for gastroscopy reports. Background technique [0002] In the medical field, medical imaging data is an important tool for doctors to diagnose diseases and provide treatment plans. In departments such as the Department of Radiology and Ultrasound, the examiner will write an examination report based on the image data of the patient's examination, so that the attending doctor can diagnose the disease and formulate a treatment plan. Writing a medical report requires the examiner to have a deep understanding of the manifestations and descriptions of disease symptoms. For inexperienced or inexperienced examiners, writing a medical report may be prone to errors. For experienced examiners, this task is also time-consuming and labor-intensive. Therefore, pr...

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
IPC IPC(8): G16H15/00G06T7/00G06T9/00G06N3/04G06N3/08
CPCG16H15/00G06T7/0012G06T9/002G06N3/08G06T2207/20221G06T2207/30092G06T2207/20081G06T2207/20084G06N3/047Y02A90/10
Inventor 丁帅杨善林曹云霞王浩刘雅静张宏敏王亚雷
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap