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

Endoscopic bronchial tumor automatic detection method and detection system

An automatic detection and bronchus technology, which is applied in the directions of catheterization, diagnostic recording/measurement, image enhancement, etc., can solve the problems that cannot reduce the work intensity of doctors and automatically detect bronchial tumors, so as to reduce computing requirements, avoid treatment opportunities, and reduce work The effect of intensity

Active Publication Date: 2019-11-15
HUNAN VATHIN MEDICAL INSTR CO LTD
View PDF24 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the doctor’s work intensity cannot be reduced and bronchial tumors can be found automatically in the real-time detection process of the existing endoscope, the purpose of the present invention is to provide an endoscopic Bronchial tumor automatic detection method and detection system

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
  • Endoscopic bronchial tumor automatic detection method and detection system
  • Endoscopic bronchial tumor automatic detection method and detection system
  • Endoscopic bronchial tumor automatic detection method and detection system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, this embodiment provides an endoscopic automatic detection method for bronchial tumors, including the following steps S101-S109.

[0058] S101. Acquire multiple endobronchial images and mark the tumor type of each endobronchial image, wherein the tumor type includes tumor-free type and tumor-bearing type, and for each tumor type, corresponding to the endobronchial image The number is not less than 300.

[0059] In the step S101, the bronchial endoscopic image is a historically acquired image obtained by using an endoscope to detect bronchial tumors. The method for marking the corresponding tumor type on the bronchial endoscope image may specifically be an artificial method. In order to ensure sufficient samples for subsequent training and to obtain a recognition model with high prediction accuracy, the number of bronchial endoscopic images corresponding to various tumor types should be no less than 300. In addition, the tumor types can be s...

Embodiment 2

[0093] Such as figure 2 As shown, this embodiment provides an endoscopic bronchial tumor automatic detection system based on the same inventive concept as compared with the first embodiment, including computer equipment for realizing the endoscopic bronchial tumor automatic detection method as described in the first embodiment , further comprising an endoscope, a transmission cable and a display screen, wherein the endoscope is communicatively connected to the computer device through the transmission cable, and the computer device is also communicatively connected to the display screen. In the specific structure of the endoscopic automatic detection system for bronchial tumors, the computer device can be, for example, a desktop computer or a handheld smart device. The endoscope is used to extend into the bronchi of the human body, and collect in real time the bronchial detection video stream that can be sent out through the transmission cable, which can be realized by using a...

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 the technical field of medical equipment, and discloses an endoscopic bronchial tumor automatic detection method and detection system. Through the method and the system, a newmethod which is based on the convolutional neural network and can replace a doctor to automatically identify the bronchial tumor condition is provided. The method comprises: firstly, performing tumorrecognition training based on a convolutional neural network method on a large number of bronchoscope images; using the training model to identify and predict the real-time detection image. An existing graph construction mode can be replaced. The tumor type is identified in bronchial real-time detection. The method not only can greatly reduce the operation demand of real-time data processing, butalso can automatically discover tumor conditions, remind doctors to further diagnose and timely diagnose the conditions, further can reduce the working intensity of the doctors, timely diagnose whether lesions occur or not, avoids delaying the treatment opportunity of the conditions, and is particularly beneficial to the discovery of early lesions.

Description

technical field [0001] The invention belongs to the technical field of medical equipment, and in particular relates to an endoscopic automatic detection method and detection system for bronchial tumors. Background technique [0002] At present, computer technology has been widely used in the medical field, that is, to use computer technology to digitally analyze medical images, and then assist clinicians to find lesions. The existing technology discloses some algorithm researches on texture features and their descriptions, including the application and improvement of algorithms, such as the method based on Gabor filter, which conforms to the characteristics of human visual perception system and the characteristics of human physiological vision. An important development direction of image analysis. The methods disclosed in the prior art have their own advantages and disadvantages, and many texture feature extraction algorithms in practical applications have problems such as ...

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): G06K9/62G06T7/11G06T7/136G06T7/194A61B5/00
CPCG06T7/11G06T7/136G06T7/194A61B5/0084G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30096G06V2201/032G06F18/2415G06F18/214
Inventor 不公告发明人
Owner HUNAN VATHIN MEDICAL INSTR CO LTD
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