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

Time series based method for positioning bleeding segments in WCE (wireless capsule endoscope) video

A technology of capsule endoscope and positioning method, applied in the field of image processing, can solve the problems of doctors' visual fatigue, missed diagnosis, misdiagnosis, etc., and achieve the effect of improving positioning efficiency and avoiding missed diagnosis and misdiagnosis.

Inactive Publication Date: 2015-12-02
SOUTHWEST JIAOTONG UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the main disadvantage of WCE examination is that due to the excessive number of frames of WCE video images, if all of them need to be detected by doctors, it will be extremely time-consuming and energy-consuming, and it will easily cause visual fatigue of doctors, and the ability to identify lesions will decrease, resulting in misdiagnosis , the occurrence of missed diagnosis

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
  • Time series based method for positioning bleeding segments in WCE (wireless capsule endoscope) video
  • Time series based method for positioning bleeding segments in WCE (wireless capsule endoscope) video
  • Time series based method for positioning bleeding segments in WCE (wireless capsule endoscope) video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] see figure 1 , is a schematic flowchart of a method for locating a bleeding segment in a time-series wireless capsule endoscope video according to an embodiment of the present invention. The method for locating the bleeding segment in this embodiment includes:

[0027] S11: Obtain the video of the wireless capsule endoscope.

[0028] Among them, wireless capsule endoscopy video usually contains 50,000-60,000 video frames.

[0029] S12: Black hole removal and edge removal are performed on the video frame of the wireless capsule endoscope video, so as to extract the intestinal mucosa image in the video frame.

[0030] Among them, the black hole removal step and the edge removal step belong to the preprocessing steps of the video frame.

[0031] Edges and black holes in the gastrointestinal tract interfere with the extraction of the intestinal mucosa in the video frame. Edges are usually caused by folds in the gut and the camera is out of focus, while black holes are u...

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 provides a time series based method for positioning bleeding segments in a WCE (wireless capsule endoscope) video. The method comprises the following steps: firstly, video frames are pre-processed, and specifically, black holes and edges are removed; then each video frame is subjected to superpixel segmentation, multiple image blocks are obtained, and whether each image block is a bleeding block or a normal block is judged according to a pre-trained color model and the color value of the image block; the red ratio characteristic value and a space characteristic value of each video frame are selected for description; finally, a red ratio characteristic value curve and a space characteristic value curve are fused averagely under time series, and the bleeding segments are determined. With adoption of the scheme, the positioning efficiency and accuracy of the bleeding segments in the WCE video can be improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for locating bleeding segments in wireless capsule endoscope video based on time series. Background technique [0002] Wireless Capsule Endoscopy (WCE) technology is a technology that uses capsule pills equipped with ultra-small cameras to obtain video images of the human digestive system. Patients start transmitting pictures within 8-12 hours after taking the capsule pills. Video images of 50,000-60,000 frames can be sent. Therefore, wireless capsule endoscopes are widely used in the analysis of digestive system diseases, especially in the detection of gastrointestinal bleeding. [0003] At present, the main disadvantage of WCE examination is that due to the excessive number of frames of WCE video images, if all of them need to be detected by doctors, it will be extremely time-consuming and energy-consuming, and it will easily cause visual fatigue of d...

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): G06T7/00G06T7/40
CPCG06T7/0012G06T2207/10016G06T2207/10068G06T2207/30028
Inventor 陈俊周陈洪瀚石玮彭强甘涛
Owner SOUTHWEST JIAOTONG UNIV
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