A multi-scale detection method and device for tumors in gastrointestinal endoscopy images

An image detection and digestive tract technology, applied in the field of multi-scale detection of tumors in endoscopic images of the digestive tract, can solve the problems of time-consuming, labor-intensive, and high labeling costs for tumors

Inactive Publication Date: 2019-06-21
SUN YAT SEN UNIV CANCER CENT
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is very time-consuming and labor-intensive to manually and accurately draw the contours of tumors i

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 multi-scale detection method and device for tumors in gastrointestinal endoscopy images
  • A multi-scale detection method and device for tumors in gastrointestinal endoscopy images
  • A multi-scale detection method and device for tumors in gastrointestinal endoscopy images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] see figure 1 , figure 1 It is a schematic flowchart of a multi-scale detection method for tumors in endoscopic images of the digestive tract disclosed in an embodiment of the present invention. Wherein, the methods described in the embodiments of the present invention are applicable to medical detection devices, medical detection equipment, or medical image processing equipment, etc., which are not specifically limited in the present invention. Such as figure 1 As shown, the multi-scale detection method for tumors in endoscopic images of the digestive tract may include the following steps:

[0078] 101. Carry out tumor image marking on each digestive tract endoscopic image sample, and perform tumor property level marking on the digestive tract endoscopic image samples marked as tumor images according to the preset tumor property level.

[0079] Among them, the gastrointestinal endoscopic image samples can be obtained from real cases of gastrointestinal tumors.

[00...

Embodiment 2

[0100] see figure 2 , figure 2 It is a schematic flowchart of another multi-scale detection method for tumors in endoscopic images of the digestive tract disclosed in an embodiment of the present invention. Among them, the gastrointestinal endoscopy image detection model includes a deep convolutional baseline neural network, a multi-classification branch network and a multi-scale detection branch network. Such as figure 2 As shown, the multi-scale detection method for tumors in endoscopic images of the digestive tract may include the following steps:

[0101] 201-202. Wherein, steps 201 to 202 are the same as steps 101 to 102 described in the first embodiment, and will not be repeated in this embodiment of the present invention.

[0102] 203. Receive the detection request sent by the endoscopic inspection equipment and the endoscopic image to be detected in real time.

[0103] In the embodiment of the present invention, a server-client platform can be built, the server...

Embodiment 3

[0132] see image 3 , image 3 It is a schematic structural diagram of a multi-scale detection device for tumors in endoscopic images of the digestive tract disclosed in an embodiment of the present invention. Such as image 3 As shown, the multi-scale detection device for tumors in endoscopic images of the digestive tract may include:

[0133] The marking unit 301 is configured to perform tumor image marking on each gastrointestinal endoscopic image sample, and perform tumor property level marking on the gastrointestinal endoscopic image samples marked as tumor images according to a preset tumor property level.

[0134] The training unit 302 is configured to train an endoscopic image detection model of the digestive tract based on the endoscopic image samples of the tumor grade marked.

[0135] The first acquiring unit 303 is configured to acquire an endoscopic image to be detected.

[0136] The second acquisition unit 304 is configured to obtain the detection result of t...

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 embodiment of the invention discloses a multi-scale detection method and device for tumors in gastrointestinal endoscopic images. The method comprises the following steps: carrying out tumor imagemarking on each gastrointestinal endoscopy image sample, and carrying out tumor property grade marking on the gastrointestinal endoscopy image sample marked as a tumor image according to a preset tumor property grade; On the basis of the gastrointestinal endoscopy image sample subjected to tumor property grade marking, obtaining a gastrointestinal endoscopy image detection model by training; Obtaining an endoscope image to be detected; And obtaining a detection result of the to-be-detected endoscopic image according to the gastrointestinal endoscopic image detection model, the detection result comprising one or more of a first classification result, a second classification result and a multi-scale tumor region detection result. By implementing the embodiment of the invention, the markingcost can be reduced, and meanwhile, the tumor region in the gastrointestinal endoscopy image can be accurately positioned.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a multi-scale detection method and device for tumors in endoscopic images of the digestive tract. Background technique [0002] According to the statistics of the World Health Organization, gastric cancer, colorectal cancer, and esophageal cancer are the three most common cancers of the digestive tract, which rank among the top six most common cancers in the world, ranking second, fourth, and fifth in China, far surpassing lung cancer in total . Moreover, the incidence rates of these three gastrointestinal cancers are on the rise in China. Since gastrointestinal cancers develop on the basis of gastrointestinal diseases (such as gastrointestinal tumors), if gastrointestinal tumors are detected early, the cure rate is extremely high, so early screening of gastrointestinal tumors is of great significance. [0003] The necessary means for early screening of gastroi...

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): G06K9/62G06N3/04G06N3/08
Inventor 徐瑞华骆卉妍李超峰徐国良
Owner SUN YAT SEN UNIV CANCER CENT
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