Automatic artery-vein name identifying method which is based on conditional random fields and used for gastric-carcinoma endoscope operation real-time navigation system

A technique of conditional random field and endoscopic surgery, applied in the fields of machine learning, minimally invasive surgery, and imaging, can solve the problem of difficulty in extracting the three-dimensional structure of blood vessels, shorten the length of hospital stay, reduce complications, and reduce hospitalization The effect of fees

Inactive Publication Date: 2018-03-13
NANFANG HOSPITAL OF SOUTHERN MEDICAL UNIV
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is not easy for surgeons to extract the 3D structure of blood vessels from CT volumes
In addition, in the narrow field of view of laparoscopy, more laparoscopic experience is needed to find a specific vascular branch structure behind the fat tissue layer, which is still a big problem for most surgeons

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
  • Automatic artery-vein name identifying method which is based on conditional random fields and used for gastric-carcinoma endoscope operation real-time navigation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The method for automatically identifying arteriovenous names based on conditional random fields in the real-time navigation system for gastric cancer laparoscopic surgery according to the present invention, such as figure 1 Shown:

[0019] 1. Data collection:

[0020] Establish criteria such as (a) pathologically confirmed primary completely resectable gastric cancer patients; (b) preoperative clinical stage: T1-4aN0-3M0; (c) abdominal enhancement less than 15 days before operation CT.

[0021] The influence of other factors on this experiment was excluded.

[0022] 2. Construction of the original 3D model:

[0023] The preoperative CT image is segmented, marked, and modeled to obtain a virtual blood vessel model.

[0024] (1) CT scan:

[0025] The patient fasted for more than 6 hours, took 500ml of warm water orally to fill the intestinal tract half an hour before the scan, and took 500ml of warm water to fill the stomach and duodenum 5 minutes before the scan.

...

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 automatic artery-vein name identifying method which is based on conditional random fields and used for a gastric-carcinoma endoscope operation real-time navigation system.The automatic artery-vein name identifying method includes the following steps that data is collected; pre-operation abdomen enhancement-stage thin-slice CT images are collected; a three-dimensional vein model is built; dendritic structures of the perigastric arteries and veins are extracted from the three-dimensional vein model, a probabilistic graphical model is built, CRF (conditional random fields), the recursive algorithm, posteriori estimation and other algorithms are adopted, and then automatic anatomy name identifying of the three-dimensional arteries and veins is achieved. Therefore,the efficiency of navigation is improved, the directions of the blood vessels are accurately guided, the success rate of operations is increased, and the application and popularization of laparoscopicgastric-carcinoma operations are facilitated.

Description

technical field [0001] The invention belongs to the fields of minimally invasive surgery, machine learning, imaging, etc., and relates to a method for automatically identifying arteriovenous names based on conditional random fields for a real-time navigation system for gastric cancer laparoscopic surgery. Background technique [0002] Gastric cancer is one of the most common tumors in my country, and radical resection is the main treatment. Laparoscopic technique is more and more applied in the field of gastrointestinal surgery because of its less trauma and helpful postoperative recovery. However, laparoscopy has its own unique limitations such as tubular field of view, lack of tactile sensation and depth sense, and the course of perigastric blood vessels is complex, with many anatomical variations. The vascular injury caused by intraoperative lymph node dissection is one of the serious complications of laparoscopic gastric cancer surgery. It is also an important reason fo...

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): A61B34/20A61B34/10
CPCA61B34/10A61B34/20A61B2034/105A61B2034/107A61B2034/2046
Inventor 陈韬
Owner NANFANG HOSPITAL OF SOUTHERN MEDICAL UNIV
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