Enteroscopy quality evaluation method and device based on image recognition and storage medium

A technology for colonoscopy examination and quality assessment, applied in the field of intelligent medical care, can solve problems such as unreasonable evaluation methods, inability to accurately reflect the quality of doctor's withdrawal of endoscopy examination, and low quality of colonoscopy examination, so as to improve the examination operation mode and shorten the intestinal Effect of microscope inspection time, complete acquisition time

Pending Publication Date: 2021-05-11
成都微识医疗设备有限公司
View PDF1 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the inventor found that there are problems with the widely used spiral retraction mirror, and the evaluation method using the total time of spiral retraction mirror as the evaluation index is unreasonable. A colonoscopy is performed to achieve a certain target, resulting in low quality colonoscopy

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
  • Enteroscopy quality evaluation method and device based on image recognition and storage medium
  • Enteroscopy quality evaluation method and device based on image recognition and storage medium
  • Enteroscopy quality evaluation method and device based on image recognition and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Such as figure 1 The shown image recognition-based colonoscopy quality assessment method includes the following steps:

[0080] Split the video captured during colonoscopy into multiple inspection images;

[0081] classifying the plurality of inspection images into close-up mode images and non-close-up mode images based on the first classification condition and the second classification condition; and

[0082] Accumulate the acquisition time of the close-range mode image, and evaluate the quality of colonoscopy based on the acquisition time of the close-range mode image;

[0083] Wherein, the first classification condition includes at least one of the clarity of the inspection image, the degree of exposure, the degree of intestinal wall shrinkage, and the degree of excrement blocking; At least one of the number and location of the lumen.

[0084] In this embodiment, the video may be a video collected in real time, and the tags of the specified number of frames in the...

Embodiment 2

[0097] On the basis of Embodiment 1, the step of classifying the inspection image first adopts the first classification condition, and then adopts the second classification condition.

[0098] In this embodiment, the plurality of inspection images are divided into invalid mode images and valid mode images based on the first classification condition, and the valid mode images are divided into close-range mode images and long-range mode images based on the second classification condition image, accumulating the acquisition duration of the close-range mode image, the acquisition duration of the distant view mode image and / or the acquisition duration of the invalid mode image, according to the acquisition duration of the close-range mode image, the acquisition duration of the perspective mode image and / or the acquisition of the invalid mode image Evaluate the quality of colonoscopies by duration.

[0099] The inspection image classification method of the above-mentioned rule of th...

Embodiment 3

[0103] On the basis of the foregoing embodiments, the second classification condition includes:

[0104] (a) The effective mode image with intestinal wall and no intestinal bag or intestinal lumen in the image content is a close-range mode image;

[0105] (b) The effective mode image with intestinal wall, intestinal bag and no intestinal lumen in the image content is a close-range mode image;

[0106] (c) Among the effective mode images with intestinal wall, intestinal pouch and intestinal cavity in the image content, and the number of intestinal pouches is 1 to 5, the effective mode image whose intestinal cavity is not located in the central area of ​​the image is a close-range mode image;

[0107] (d) The rest of the effective mode images are vision mode images.

[0108] The traditional spiral retraction requires the endoscope to be aimed at the intestinal wall or the intestinal bag, so that the intestinal mucosa can be better observed, such as Figure 4 shown. Therefore,...

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 an enteroscopy quality evaluation method and device based on image recognition and a storage medium. The evaluation method comprises the following steps: splitting a video acquired in an enteroscopy process into a plurality of examination images; dividing the plurality of inspection images into close-shot mode images and non-close-shot mode images based on the first classification condition and the second classification condition; and accumulating the collection duration of the close-shot mode image, and evaluating the enteroscopy quality based on the collection duration of the close-shot mode image. According to the method, the collection time of the close-shot mode image is used as an evaluation index, a scientific and reasonable enteroscopy quality evaluation standard is established, and an endoscopy doctor can be guided to improve the collection time of the close-shot mode image by changing an examination operation mode within a shorter enteroscopy time; furthermore, a longer close-range view field capable of effectively observing intestinal mucosa is obtained, so that the examination quality of the enteroscope is improved.

Description

technical field [0001] The invention relates to the field of intelligent medical technology, in particular to an image recognition-based colonoscopy quality assessment method, device and storage medium. Background technique [0002] Colorectal cancer develops from precancerous lesions and early cancers such as dead adenomatous polyps, and is a malignant tumor with the highest incidence rate both at home and abroad. Timely screening, discovery and removal of adenomatous polyps is an effective way to prevent colorectal cancer and reduce the risk of death from colorectal cancer. [0003] Colonoscopy screening is the benchmark for colorectal cancer screening. Colonoscopy screening includes observation during the process of entering and withdrawing the scope. The observation quality of colonoscopy is very important, and it is the main factor affecting the adenoma detection rate (ADR) and average adenoma detection rate (adenoma per colonoscopy, APC). [0004] At present, there i...

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): G06T7/00A61B1/31
CPCG06T7/0012A61B1/31G06T2207/10016G06T2207/10068G06T2207/30028G06T2207/30096A61B1/00009G06T7/00G06T2207/20076G06T2207/20064G06T2207/30168G06T2207/20072G16H50/20G16H30/40G16H20/40G16H40/20G06T2207/20084A61B1/0005
Inventor 肖潇刘敬家
Owner 成都微识医疗设备有限公司
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