Ultrasound-assisted muscle recognition method, system and auxiliary injection device

An ultrasound-assisted and recognition method technology, which is applied in subcutaneous injection devices, neural learning methods, ultrasound/sonic/infrasonic diagnosis, etc., can solve problems such as unclear muscle boundaries, shorten the learning cycle, avoid damage, and improve safety. Effect

Active Publication Date: 2021-06-22
SHANDONG UNIV QILU HOSPITAL
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem of unclear muscle boundaries in ultrasound images, the present disclosure provides an ultrasound-assisted muscle recognition system, which can indicate the contour of the target muscle in ultrasound images, thereby improving the accuracy of injection, and can be used for training and improving injection efficiency

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
  • Ultrasound-assisted muscle recognition method, system and auxiliary injection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] An ultrasound-assisted muscle recognition method is provided in this embodiment, including: a training phase and an application phase; wherein, the training phase includes: constructing a deep learning model and obtaining a training sample; the training sample is a muscle ultrasound image with a known name;

[0045] In this embodiment, a convolutional neural network is used as a learning model, and training samples are input into the learning model for training to obtain a trained deep learning model, namely: an ultrasound-assisted muscle recognition model;

[0046] Among them, the application stage includes: inputting the ultrasonic image to be recognized into the trained deep learning model, and outputting the muscle outline in the ultrasonic image to be recognized.

[0047] The concrete steps of described training are as follows:

[0048] (3) Preprocessing the ultrasonic image, including graying the ultrasonic image, denoising the image, enhancing the contrast, and p...

Embodiment 2

[0053] An ultrasound-assisted muscle recognition system is provided in this embodiment, including: a training module and an application module;

[0054] Wherein, the training module includes: a construction unit, which is configured to: construct a deep learning model, and obtain a training sample; the training sample is an ultrasound image that has marked muscle contours;

[0055] The training unit is configured to: input the training samples into the deep learning model for training, and obtain the trained deep learning model, namely: the ultrasound-assisted muscle recognition model;

[0056] Among them, the application module includes:

[0057] The identification unit is configured to: input the ultrasound image to be identified into the trained deep learning model, and output the muscle contour in the ultrasound image to be identified; the training method of the deep learning model is carried out using the method in embodiment 1 .

Embodiment 3

[0059] This embodiment provides a storage medium, on which there are computer instructions, and the computer instructions are executed as in the method for establishing a deep learning model in Embodiment 1.

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 disclosure belongs to the technical field of precision injection, and in particular relates to an ultrasound-assisted muscle recognition method, system and auxiliary injection device. Botulinum toxin has good curative effect when applied to diseases such as dystonia, and is currently one of the preferred methods in the field of neurology and rehabilitation medicine to relieve muscle spasms such as stroke, cerebral palsy, traumatic brain injury and spinal cord injury. The precise botulinum toxin treatment technology through ultrasound and myoelectric stimulation has become a hot research direction of botulinum toxin treatment. Since the boundaries of muscles in ultrasound images are not clear, there is still a high probability of injection errors. Using image recognition technology to mark the contours of target muscles can effectively improve the accuracy of injections. The present disclosure provides a method for constructing a muscle model through ultrasound recognition. The deep learning model is trained by collecting muscle ultrasound images of known individuals, so as to realize the recognition of muscle contours of unknown individuals, improve injection accuracy, and be used in clinical treatment and teaching. aspects are of great significance.

Description

technical field [0001] The disclosure belongs to the technical field of precision injection, and in particular relates to an ultrasound-assisted muscle identification method, an ultrasound-assisted muscle identification system, and an ultrasound-assisted muscle botulinum toxin injection device. Background technique [0002] The information disclosed in this Background section is only intended to increase the understanding of the general background of the disclosure, and is not necessarily to be taken as an acknowledgment or any form of suggestion that the information constitutes prior art that is already known to those skilled in the art. [0003] Since the FDA approved the marketing of botulinum toxin, it has a clear curative effect when applied to dystonia diseases. It can effectively reduce local muscle tension, improve joint mobility, improve gait, posture, etc. It is one of the first-choice methods for muscle spasms such as spinal cord injury and spinal cord injury, and...

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): A61B5/00A61B8/00G06N3/08A61M5/42G06T11/00G06T7/00
CPCA61M5/427
Inventor 张杨胡静璐
Owner SHANDONG UNIV QILU HOSPITAL
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