Method and system for generating structured diagnosis report of digestive endoscopy based on image recognition

A diagnostic report and image recognition technology, applied in the field of artificial intelligence, can solve problems such as difficulty in realizing endoscopic description and diagnosis standardization, standardization, low efficiency, and time-consuming, so as to reduce writing workload, improve work efficiency, and The effect of medical services

Active Publication Date: 2021-05-28
SHANDONG UNIV QILU HOSPITAL +1
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the subjective judgment of doctors is easy to change with the level of doctors, working status and other factors, resulting in the omission of diagnostic descriptions
It takes a lot of time for the doctor to actively operate the computer input device to write the diagnosis report, and the efficiency is not high
Doctors write diagnostic reports based on subjective judgments and operating computer input devices, which is difficult to achieve standardization and standardization of endoscopic description and diagnosis, and is not conducive to patients' visits and follow-ups between different hospitals.

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
  • Method and system for generating structured diagnosis report of digestive endoscopy based on image recognition
  • Method and system for generating structured diagnosis report of digestive endoscopy based on image recognition
  • Method and system for generating structured diagnosis report of digestive endoscopy based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 As shown, this embodiment discloses a method for generating a structured diagnostic report for digestive endoscopy based on image recognition, including the following steps:

[0047] Step 1: Obtain the video data collected during the gastrointestinal endoscopy operation, as well as the operator's voice data;

[0048] The above video data and voice data are all acquired during the operation of the endoscope, and are correlated through time.

[0049] Step 2: performing current part identification and lesion identification for each video frame according to the video data; performing voice recognition according to the voice data;

[0050] (1) The method for carrying out current part recognition to video frame comprises:

[0051] (1.1) Building a training set

[0052] Collect pictures of various parts of gastroscopy and colonoscopy, screen the images of digestive tract parts, mark the categories to be identified and identify the auxiliary categories of in...

specific Embodiment approach

[0067] As a specific implementation, the process of judging an image as a non-similar image is:

[0068] The hash sequence is generated by the mean hash algorithm and the Hamming distance is calculated. When the Hamming distance is greater than the set Hamming distance threshold, the image is judged as a non-similar image.

[0069] The similarity calculation logic generates a hash sequence through the mean hash algorithm and calculates the Hamming distance. When the Hamming distance is greater than the set threshold, the image is judged as a non-similar image. The relevant algorithms are as follows:

[0070] (a) Mean Hash Algorithm

[0071] Scaling: The picture is scaled to 8*8, the structure is preserved, and the details are removed.

[0072] Grayscale: convert to 256-level grayscale image.

[0073] Average: Calculate the average of all pixels in the grayscale image.

[0074] Comparison: if the pixel value is greater than the average value, it will be recorded as 1, other...

Embodiment 2

[0115] The purpose of this embodiment is to provide a system for generating a structured diagnostic report for digestive endoscopy based on image recognition, including:

[0116] The endoscopic image acquisition module acquires the video data collected during the digestive tract endoscopic operation;

[0117] The operator's voice acquisition module acquires the operator's voice data during the digestive tract endoscopy operation;

[0118] The current part recognition module, according to the video data, performs current part recognition for each video frame;

[0119] The lesion identification module performs focus identification for each video frame according to the video data;

[0120] The speech keyword recognition module recognizes the keywords related to medicine according to the speech data;

[0121] The structured report generation module, according to the identified parts and lesions, as well as keywords, combined with the medical knowledge base, generates correspondi...

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 discloses a method and system for generating a structured diagnosis report of digestive endoscopy based on image recognition. The method includes the following steps: acquiring video data collected during the operation of digestive tract endoscopy; according to the video data, for each The video frame is used for current part identification and lesion identification; according to the identified parts and lesions, combined with the medical knowledge base, corresponding descriptive text is generated and added to the structured template to obtain a diagnosis report. The invention can automatically generate a natural language description text based on the endoscopic video to obtain a structured diagnosis report, improve the standardization and normalization degree of the diagnosis report, and improve the work efficiency of doctors.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and system for generating a structured diagnosis report of digestive endoscopy based on image recognition. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] The currently clinically applied digestive endoscopy diagnostic report system provides physicians with the function of writing diagnostic reports. The formation process of the diagnosis is formed by the subjective judgment of the endoscopist according to the inspection process; the writing process of the diagnosis report is completed by the physician actively operating the computer mouse, keyboard and other input devices. [0004] However, the subjective judgment of physicians is likely to cause omissions in diagnostic descriptions due to changes in the ...

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 Patents(China)
IPC IPC(8): G16H15/00G06F40/186G06F16/36G06F40/295G06N3/04
CPCG16H15/00G06F16/367G06N3/045
Inventor 冯健左秀丽戚庆庆赖永航李延青李真杨晓云邵学军辛伟
Owner SHANDONG UNIV QILU HOSPITAL
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