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

Carpal canal image segmentation method and system based on neural network

An image segmentation and neural network technology, applied in the field of medical image processing, can solve the problem of time-consuming and labor-intensive manual segmentation of carpal tunnel images, and achieve high accuracy and improve accuracy.

Pending Publication Date: 2021-10-01
THE FIRST AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, manual segmentation of carpal tunnel images is time-consuming and labor-intensive, and different doctors may obtain different results when performing image segmentation, even if the same doctor segments the same hand MRI image at different time periods, there will be subtle differences

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
  • Carpal canal image segmentation method and system based on neural network
  • Carpal canal image segmentation method and system based on neural network
  • Carpal canal image segmentation method and system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] Such as figure 1 Shown a kind of carpal tunnel image segmentation method based on neural network, this method comprises the following steps:

[0073] Constructing and training a processing model using a convolutional neural network, the processing model includes at least a classification module and a segmentation module;

[0074] Obtain the carpal tunnel image to be segmented;

[0075] Preprocessing the carpal tunnel image to be segmented;

[0076] Use the classification module to perform morphological classification on the preprocessed image;

[0077] According to the result of morphological classification, the carpal tunnel image to be segmented is segmented using the adapted segmentation module and the segmentation result is output.

[0078] Using the above method, a carpal tunnel image segmentation system based on neural network such as figure 2 shown, including:

[0079] The input module 1 is used to obtain the carpal tunnel image to be segmented;

[0080] P...

Embodiment 2

[0085] Such as figure 1 Shown a kind of carpal tunnel image segmentation method based on neural network, this method comprises the following steps:

[0086] Constructing and training a processing model using a convolutional neural network, the processing model includes at least a classification module and a segmentation module;

[0087] Obtain the carpal tunnel image to be segmented;

[0088] Preprocessing the carpal tunnel image to be segmented;

[0089] Use the classification module to perform morphological classification on the preprocessed image;

[0090] According to the result of morphological classification, the carpal tunnel image to be segmented is segmented using the adapted segmentation module and the segmentation result is output.

[0091] Wherein, the processing model includes a plurality of segmentation modules, which are used to segment carpal tunnel images of different shapes to be segmented according to the shape classification results and output the segmen...

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 carpal canal image segmentation method based on a neural network, comprising the following steps: using a convolutional neural network to construct and train a processing model, the processing model at least comprising a classification module and a segmentation module; obtaining a carpal canal image to be segmented; preprocessing the carpal canal image to be segmented; performing form classification on the preprocessed image by using a classification module; and according to the form classification result, segmenting the to-be-segmented carpal canal image by using an adaptive segmentation module and outputting a segmentation result. According to the method, the to-be-segmented carpal canal image is classified and then segmented, the accuracy of the processing model for carpal canal image segmentation is improved, the deep learning image processing technology is applied to medical image processing based on the processing model constructed and trained by the convolutional neural network, the high accuracy of the segmentation result is utilized, and end-to-end carpal canal image segmentation is realized, so that doctors without professional experience can complete diagnosis of carpal canal syndromes.

Description

technical field [0001] The invention relates to a carpal tunnel image segmentation method and system, in particular to a neural network-based carpal tunnel image segmentation method and system, belonging to the technical field of medical image processing. Background technique [0002] Carpal tunnel syndrome is caused by the compression of the median nerve when it passes through the carpal tunnel. It is manifested as pain, numbness, and muscle weakness in the innervated area. It is the most common compressive focal mononeuropathy clinically, and its incidence is increasing year by year. Early non-surgical treatment can bring certain curative effect, and more patients can obtain significant improvement of symptoms from surgical treatment. However, due to the non-specificity of symptoms, misdiagnosis and missed diagnosis occur from time to time, and the delay in diagnosis leads to the continuous progression of the disease, which will eventually develop into irreversible nerve 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): G06T7/00G06T7/10G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/10G06N3/08G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30101G06N3/045G06N3/048G06F18/241
Inventor 卢荟周海英蒋帅胡贤良白琪金倩君
Owner THE FIRST AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
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