Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method and system for automatically identifying biopsy sites and biopsy quantities under endoscopy

A technology of automatic recognition and action recognition, applied in biometric recognition, character and pattern recognition, computer components, etc., can solve the problems of increasing the burden on endoscopists and easily confusing parts of materials, and achieve the effect of positive and efficient promotion

Active Publication Date: 2021-02-05
SHANDONG UNIV QILU HOSPITAL +1
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] According to the standardized writing requirements for biopsy applications, endoscopists should accurately provide pathologists with the location, quantity, and endoscopic findings of the specimens submitted for examination. Currently, the biopsy locations and the number of blocks are manually counted and recorded, and not only are there easy to confuse the sampling locations, etc. risk, and increases the burden on endoscopists

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
  • A method and system for automatically identifying biopsy sites and biopsy quantities under endoscopy
  • A method and system for automatically identifying biopsy sites and biopsy quantities under endoscopy
  • A method and system for automatically identifying biopsy sites and biopsy quantities under endoscopy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 As shown, this embodiment discloses a detection method for automatically identifying biopsy sites and biopsy quantities under an endoscope, including a training stage and an inference stage.

[0033] (1) Training stage

[0034] Step 1: Obtain endoscopic biopsy forceps to collect video clips, and perform image sampling and labeling processing.

[0035] Step 101: based on the development interface of the video capture card, manually collect biopsy video clips and endoscopic images with biopsy forceps in real time, and simultaneously collect an equal number of video clips without biopsy;

[0036] Step 102: Evenly sample n frames (16 frames) of the collected video clips through video frame division

[0037] , use LabelImg and other tools to annotate the biopsy image, and generate an annotation file with the .xml suffix;

[0038] Step 103: No data enhancement or processing is performed on the endoscopic biopsy image, only the image is scaled to 300X300, a...

Embodiment 2

[0073] The purpose of this embodiment is to provide a system for automatically identifying the biopsy site and the number of biopsies under the endoscope.

[0074] A system for automatically identifying the biopsy site and the number of biopsies under an endoscope, comprising:

[0075] The image acquisition module acquires video frames collected in real time during the endoscopic examination;

[0076] The biopsy forceps detection module, based on the pre-trained biopsy forceps detection model, detects whether there is a biopsy forceps frame by frame;

[0077] The biopsy site identification module is used to determine the current endoscopic site for biopsy based on the pre-trained endoscopic site identification model when there is a biopsy forceps;

[0078] The biopsy action recognition module is used to track the biopsy forceps when there is a biopsy forceps to obtain continuous video clips containing the biopsy forceps, and determine whether to perform biopsy according to th...

Embodiment 3

[0082] The purpose of this embodiment is to provide an electronic device.

[0083] An electronic device, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, the following steps are implemented, including:

[0084] Obtain video frames collected in real time during the endoscopic examination;

[0085] Based on the pre-trained biopsy forceps detection model, detect the presence of biopsy forceps frame by frame;

[0086] If there is biopsy forceps, based on the pre-trained endoscopic site recognition model, determine the current endoscopic site for biopsy; at the same time, start tracking the biopsy forceps to obtain continuous video clips containing the biopsy forceps Action recognition model to determine whether to take a biopsy.

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 automatically identifying the biopsy site and the number of biopsies under an endoscope. The method includes the following steps: obtaining video frames collected in real time during the endoscopic examination; Frame detection whether there is a biopsy forceps; if there are biopsy forceps, based on the pre-trained endoscopic part recognition model, determine the current endoscopic site for biopsy; at the same time, start tracking the biopsy forceps to obtain continuous video clips containing the biopsy forceps , according to the pre-trained biopsy action recognition model, determine whether to perform biopsy. The invention can accurately detect and track the biopsy forceps and determine the biopsy site, and at the same time accurately infer the biopsy scene and count the number of biopsy times, thereby providing a guarantee for standardized pathological reports.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and system for automatically identifying biopsy sites and biopsy quantities under an endoscope. 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] Endoscopic biopsy is currently an indispensable means for the early diagnosis and treatment of digestive system diseases. When suspicious lesions are found during endoscopic examination, in order to clarify the nature, distribution and extent of the lesions, it is often necessary to perform multiple biopsies in multiple parts of the gastrointestinal mucosa , which not only provides clues for disease diagnosis, but also understands the development trend of the disease and judges the prognosis. [0004] According to the standardized writing requirements for biopsy ap...

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): G06K9/00G06K9/62A61B10/04A61B10/06G06N3/04
CPCA61B10/04A61B10/06G06V40/10G06V40/14G06N3/045G06F18/214
Inventor 李真冯健左秀丽阿迪莱李延青杨晓云赖永航邵学军
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
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