An endoscopic image processing method and related equipment

An image processing and endoscopy technology, applied in the field of image processing, can solve the problems of low accuracy of endoscopy image detection algorithm

Active Publication Date: 2021-09-10
TSINGHUA BERKELEY SHENZHEN INST
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing technology, the accuracy of the endoscopic imag...

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
  • An endoscopic image processing method and related equipment
  • An endoscopic image processing method and related equipment
  • An endoscopic image processing method and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] refer to figure 1 , figure 1 It is a method flowchart of an embodiment of an endoscopic image processing method in the present invention, a kind of endoscopic image processing method, comprising:

[0039] Image acquisition step S11: acquire an endoscopic image to be processed, wherein an endoscope (that is, an endoscope) is used to acquire tissue images of the digestive tract and other positions as the endoscopic image to be processed;

[0040] Image preprocessing step S12: performing image unification processing and / or data enhancement processing on the endoscopic image to be processed, image unification processing is to unify the data format and image format of the endoscopic image to be processed, and data enhancement processing, That is, data augmentation is to use data enhancement technology to process endoscopic images to be processed to generate more endoscopic images to achieve image augmentation, including flipping, cropping, rotating, zooming and other operat...

Embodiment 2

[0056] Embodiment 2 is provided based on Embodiment 1, and the embodiment provides an endoscopic image processing device, referring to image 3 , image 3 It is a structural block diagram of an embodiment of an endoscopic image processing device in the present invention, including:

[0057] An image acquisition module 31, configured to acquire endoscopic images to be processed;

[0058] An image preprocessing module 32, configured to perform image unification processing and / or data enhancement processing on the endoscopic images to be processed;

[0059] The detection module 33 is used to input the to-be-processed endoscopic image processed by the image preprocessing module to the convolutional neural network obtained based on migration learning training for detection, and obtain the image type of the to-be-processed endoscopic image, and the image type includes Normal images and abnormal images; in addition, the convolutional neural network also performs abnormal region det...

Embodiment 3

[0063] Embodiment 3 is provided based on Embodiment 1. Embodiment 3 provides a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to perform as described endoscopic image processing method. For a specific description of the endoscopic image processing method, refer to the description of Embodiment 1, and details are not repeated here.

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 endoscopic image processing method and related equipment. The invention obtains the endoscopic image to be processed, and then detects the endoscopic image to be processed according to the convolutional neural network based on transfer learning training, and obtains the obtained endoscopic image. The image type of the endoscopic image, the image type includes normal image and abnormal image, overcomes the technical problem of low accuracy of the endoscopic image detection algorithm in the existing technology, combined with transfer learning and convolutional neural network, not only effectively improves the endoscopic image The accuracy of image type detection, and the image type based on detection can help doctors diagnose and treat, reduce the workload of doctors, improve the abnormal detection rate, and reduce the abnormal missed detection rate.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an endoscopic image processing method and related equipment. Background technique [0002] For operations such as gastrointestinal endoscopy and natural orifice endoscopic surgery, doctors perform inspections, diagnoses, and operations based on personal experience, which may easily lead to missed diagnosis, misdiagnosis, and surgical errors, posing a threat to the personal safety of patients. With the development of science and technology, in order to reduce the error of manual detection, computer-aided diagnosis technology has emerged, using image detection algorithms to assist doctors in the examination and treatment of patients. However, in the prior art, the accuracy of the endoscopic image detection algorithm is still low, and it is urgent to improve this technology. Contents of the invention [0003] The present invention aims to solve one of the technical problems in rel...

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
IPC IPC(8): G06K9/62A61B1/00A61B1/04
CPCA61B1/00057A61B1/04A61B1/0002G06V2201/03G06F18/24G06F18/214
Inventor 徐弢张子琪赵文祥
Owner TSINGHUA BERKELEY SHENZHEN INST
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