Multi-classifier wrist bone grade recognition method based on height and age

A multi-classifier and recognition method technology, applied in the field of level recognition, can solve the problem of low classification accuracy of each bone level in the left hand, and achieve the effect of reducing the decline in model accuracy, reducing errors, and improving accuracy

Active Publication Date: 2019-07-02
浙江康体汇科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the problem that the existing deep learning model has a low classification accur

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0018] The present embodiment provides a multi-classifier wrist bone grade recognition method based on height and age, comprising the following steps:

[0019] Step 1. Number the 14 bones in the carpal X-ray in sequence. The 14 bones are: radius, palm 1, palm 3, palm 5, near 1, near 3, near 5, middle 3, middle 5 , far 1, far 3, far 5, capitate, hamate, number these 14 bones from 1 to 14 in sequence; use Ni to represent the total grade number of the i-th bone in the CHN bone age assessment method, i= 1,...,14;

[0020] Step 2. For i=1, ..., 14 in turn, according to the actual situation, a batch of i-th bone slice sample sets whose height, age and grade have been calibrated are used to train to obtain a regression model Mi based on a deep learning network;

[0021] Step 3. For i=1, ..., 14 in turn, according to the actual situation, a batch of i-th bone slice sample sets whose bone grades have been calibrated are used to train to obtain the following three-category deep learnin...

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 multi-classifier wrist bone grade recognition method based on height and age. According to the method, on the basis of a deep learning network regression model based on height and age information and a plurality of three-classification deep learning network classification models, an approximate range of grades is obtained through the regression model, and then corresponding classifiers are selected to accurately classify the grades of bones. According to the method, the bone age grade judgment accuracy can be effectively improved, and the final bone age judgment erroris reduced.

Description

technical field [0001] The invention relates to the technical field of bone age grade assessment, in particular, the invention relates to a multi-classifier wrist bone grade recognition method based on height and age. Background technique [0002] Bone age is an ideal indicator for evaluating biological age and is widely used in fields such as medicine, sports and forensic identification. In the medical field, bone age is mainly used in the diagnosis and treatment of endocrine and growth and development diseases, as well as in surgical operations such as spine correction and lower limb balance. In the field of sports, bone age is mainly used to eliminate age fraud and standardize the order of competitions; to determine the developmental level of athletes and formulate scientific training methods; as an indicator for athlete selection, to select sports talents. In the field of forensic identification, bone age is mainly used to identify the age of criminal suspects or the de...

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): G06K9/62
CPCG06F18/2431
Inventor 毛科技丁维龙赵小敏万臧鑫陈立建
Owner 浙江康体汇科技有限公司
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