Method for avoiding bifurcation of veins and venipuncture robot

A venous bifurcation and venipuncture technology, applied in the field of image recognition, can solve the problems of not taking into account the venous bifurcation structure, the increased risk of puncture failure, etc., to improve cognition and decision-making ability, and accurate venous bifurcation detection and avoidance results. , fast effect

Active Publication Date: 2022-04-05
TONGJI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The system does not take into account the vein bifurcation structure when making puncture decisions, and the system may choose the best puncture location near the vein bifurcation, resulting in an increased risk of puncture failure

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
  • Method for avoiding bifurcation of veins and venipuncture robot
  • Method for avoiding bifurcation of veins and venipuncture robot
  • Method for avoiding bifurcation of veins and venipuncture robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] This embodiment provides a method for avoiding venous bifurcations, the method comprising:

[0045] Step S1: Obtaining vein images, the vein images are visible light images or infrared images, the visible light images are acquired by a camera, and the infrared images are acquired by an infrared camera.

[0046] Step S2: Obtain the vein bifurcation position in the vein image through deep reinforcement learning, and the expression of deep reinforcement learning is:

[0047] Q new (S t ,A t )←Q old (S t ,A t )+α·[Q target (S t ,A t )-Q old (S t ,A t )]

[0048] Q target (S t ,A t ) = R t+1 +γ·Q max (S t+1 ,A)

[0049] Among them, Q is the state-action value function of the vein, α is the learning rate, γ is the attenuation factor, S t is the current state, A t is the action selected according to the behavior strategy, A is the action with the largest Q value selected by the greedy strategy, R t+1 To perform action A t The final reward, the size of th...

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 present invention relates to a vein bifurcation avoidance method and a venipuncture robot. The method includes: S1: acquiring a vein image; S2: obtaining the vein bifurcation position in the vein image through deep reinforcement learning; S3: judging whether the action point is located at the vein bifurcation Within the scope of influence, if yes, change the position of the action point, if not, complete the vein bifurcation avoidance; the venipuncture robot includes a vein bifurcation avoidance module, and the vein bifurcation avoidance module executes the vein bifurcation avoidance method. Vein bifurcation detection and avoidance results are more accurate compared to existing techniques.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a vein bifurcation avoidance method and a venipuncture robot. Background technique [0002] Pricking a needle at a vein bifurcation can easily lead to problems such as puncturing blood vessels, so it is necessary to avoid this structure in general venipuncture operations. [0003] Patent CN210095745U discloses an automatic needle pricking device, including: a bracket, at least one pressurizing device, a scanning device, a clamping module, an automatic needle ejecting device, a control driving module and a human-computer interaction module. The device needs to manually select the puncture position during use, without realizing automation, and there is no autonomous identification and active puncture avoidance of vein bifurcations. [0004] Patent CN111096796A proposes a multi-layer control system for a fully automatic venipuncture robot, including: a perception decision-making la...

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 Patents(China)
IPC IPC(8): A61B17/34A61B34/10A61B34/20A61B34/30G06T7/70G06N3/08
CPCA61B17/3403A61B34/10A61B34/20A61B34/30G06T7/70G06N3/08A61B2034/2065A61B2034/107A61B2034/108A61B2034/2055G06T2207/10048G06T2207/30101
Inventor 齐鹏曹旭
Owner TONGJI 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