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

Method and device for detecting osteoporosis by using CT (Computed Tomography) image

A CT image and osteoporosis technology, applied in the fields of artificial intelligence and medical treatment, can solve problems such as difficulty in quickly meeting medical needs, subjective errors in diagnostic results, and long training cycles for doctors, so as to alleviate the shortage of medical resources, the amount of parameters, and the amount of calculations Less, to achieve the effect of repeated use

Active Publication Date: 2022-02-18
珠海仁康医疗器械有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accuracy of this method of diagnosis depends on the doctor's own work experience. For young doctors with little experience, there are certain subjective errors in the diagnosis results.
However, mature doctors have a long training cycle, and it is difficult to quickly meet the growing medical needs

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 and device for detecting osteoporosis by using CT (Computed Tomography) image
  • Method and device for detecting osteoporosis by using CT (Computed Tomography) image
  • Method and device for detecting osteoporosis by using CT (Computed Tomography) image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] On the basis of the pytorch framework, use python to build ResNet18 and such as figure 1 The super-resolution reconstruction network shown. It should be noted that, if necessary, other image classification networks can also be used instead of ResNet18. In this embodiment, the shallow feature extraction unit 2 is a 3*3 convolutional layer, and the number of channels of the output shallow feature map is 64. The deep feature extraction unit 3 includes four MSRB modules 31 and four corresponding AEMSRB modules 32, the positions of the short skip connections 33 and the long skip connections 34 are as follows figure 1 shown. Wherein, the internal structure of the MSRB module 31 is as follows figure 2 As shown, the internal structure of AEMSRB module 32 is as follows image 3 As shown, the internal structure of the MFM fusion module 321 is as follows Figure 4 As shown, the internal structure of the first branch 323 of the channel attention module 322 is as follows Fig...

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 discloses a method and device for detecting osteoporosis by using a CT image. The method comprises the steps: carrying out the super-resolution reconstruction of a lumbar vertebra sample CT image, classifying a lumbar vertebra reconstruction image through ResNet18, and the like. The super-resolution reconstruction network comprises a shallow feature extraction unit, a deep feature extraction unit and an image reconstruction unit, an MSRB module and an AEMSRB module which are symmetrical are arranged in the deep feature extraction unit, the AEMSRB module is connected to the downstream of the MSRB module, and a feature map output by the MSRB module is input into the corresponding AEMSRB module through short jump connection; the super-resolution reconstruction network has the advantages of being high in feature fusion efficiency, small in parameter amount and calculation amount, good in reconstruction effect and the like, the quality of an image input into the ResNet18 is improved, the accuracy of the ResNet18 on an image classification result is improved, then the accuracy of detecting the osteoporosis condition of the body of a patient is improved, the actual diagnosis and treatment requirements are met, and the method is suitable for popularization and application. And the situation of shortage of medical resources is relieved.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and medical technology, and in particular relates to a method and a device for detecting osteoporosis using CT images. Background technique [0002] Clinically, the diagnosis of osteoporosis is basically judged by the doctor's visual inspection of the patient's medical images. Since the performance on the lumbar spine is more obvious, the lumbar spine is usually used as a representative to diagnose the patient's overall bone condition. However, the accuracy of diagnosis in this way depends on the work experience of the doctor himself. For young doctors with little experience, there are certain subjective errors in the diagnosis results. However, the training period for mature doctors is long, and it is difficult to quickly meet the growing medical needs. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a method ...

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): G06T7/00G06T3/40G06N3/08G06N3/04G06V10/44G06V10/82
CPCG06T7/0012G06T3/4053G06N3/08G06T2207/10081G06T2207/20221G06T2207/30008G06N3/048G06N3/045
Inventor 袁兰
Owner 珠海仁康医疗器械有限公司
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