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

Intelligent target detection system and method for gastroscope images

A technology of target detection and gastroscope, applied in the field of target detection, can solve problems such as reducing subjective and artificial diagnostic errors, and achieve the effect of reducing diagnostic errors

Pending Publication Date: 2022-01-28
BEIJING HOSPITAL
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, there is no gastroscope image intelligent target detection system and method that combines the target detection technology with the gastroscope image detected by the gastroscope to realize the identification of early gastric cancer and reduce the diagnostic error caused by subjective and artificial

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
  • Intelligent target detection system and method for gastroscope images
  • Intelligent target detection system and method for gastroscope images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 As shown, this embodiment provides a gastroscope image intelligent target detection system, including an image acquisition module and a target detection module. Wherein, the image acquisition module is used to acquire the gastroscope image to be detected; the object detection module is used to output the gastroscope image to be detected to the object detection model to obtain the lesion area and the lesion category corresponding to the lesion area.

[0056] The training process of the target detection model is:

[0057]Step 1, determine a plurality of first gastroscopy images. The first gastroscopic image includes a white light image, a blue laser imaging technology image, and an endoscopic linked imaging mode image. Specifically, the linkage imaging mode under the endoscope adopts laser projection with a wavelength of 410nm and adds a red signal, which can obtain stronger contrast than white light images, and can see the microvascular structure and s...

Embodiment 2

[0081] Such as figure 2 As shown, the present embodiment provides a method for intelligent target detection in gastroscopy images, including:

[0082] Step 100, acquiring an image of the gastroscope to be detected.

[0083] Step 200, output the gastroscope image to be detected to a target detection model to obtain a lesion area and a lesion category corresponding to the lesion area.

[0084] The training process of the target detection model is: determine multiple first gastroscope images; determine the label corresponding to each of the first gastroscope images; the label includes lesion category and lesion area; the first gastroscope image and the The label corresponding to the first gastroscope image is input into the convolutional neural network to train the convolutional neural network, and then obtain the target detection model.

[0085] Further, the outputting the gastroscope image to be detected to the target detection model to obtain the lesion area and the lesion ...

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 an intelligent target detection system and method for gastroscope images, belonging to the technical field of target detection. The system comprises: an image acquisition module, which used for acquiring a to-be-detected gastroscope image; and a target detection module, which is used for outputting the to-be-detected gastroscope image to a target detection model to obtain a lesion area and a lesion category corresponding to the lesion area. The training process of the target detection model comprises the following steps: determining a plurality of first gastroscope images; determining a label corresponding to each first gastroscope image, wherein the label comprises a lesion category and a lesion area; and inputting the first gastroscope images and the labels corresponding to the first gastroscope images into a convolutional neural network to train the convolutional neural network, thereby acquiring the target detection model. The target detection model is obtained by combining the target detection method with the gastroscope images, so intelligent detection of the lesion area in the gastroscope images and the lesion types corresponding to the lesion areas is realized, and diagnosis errors caused by human subjectivity are reduced.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to an intelligent target detection system and method for gastroscope images. Background technique [0002] Early diagnosis and early treatment of gastric cancer depend on the timely detection and correct diagnosis of early gastric cancer under endoscopy. However, most early gastric cancer symptoms are hidden, and there are certain difficulties in diagnosing gastric cancer through the most commonly used white-light gastroscopy in clinical practice. At the same time, the current diagnosis method greatly depends on the subjective judgment of doctors, and the false negative rate of gastric cancer detected by gastroscopy is 4.6-25.8%. If the doctor is inexperienced or in poor condition, it is likely to have an impact on the diagnosis result. Once a misdiagnosis or missed diagnosis occurs, it will cause great harm to the patient. [0003] In recent years, with the development of...

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): G06T7/00G06V10/25G06V30/19G06N3/04G06N3/08
CPCG06T7/0012G06N3/08G06T2207/30092G06N3/045G06F18/241G06F18/214
Inventor 赵莉孙雪王青杨吉江
Owner BEIJING 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