Unlock instant, AI-driven research and patent intelligence for your innovation.

An Adaptive Extraction Method of Wrist Reference Bone Feature Area

A feature area, self-adaptive technology, applied in neural learning methods, computer components, image enhancement, etc., can solve the problem of low accuracy, achieve the effect of improving recognition accuracy and having universal applicability

Active Publication Date: 2022-03-01
ZHEJIANG UNIV OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of the low accuracy rate of the existing wrist reference bone extraction method, the present invention provides a high accuracy wrist reference bone feature region extraction method

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
  • An Adaptive Extraction Method of Wrist Reference Bone Feature Area
  • An Adaptive Extraction Method of Wrist Reference Bone Feature Area
  • An Adaptive Extraction Method of Wrist Reference Bone Feature Area

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The technical solution of the present invention will be further elaborated below in conjunction with the accompanying drawings.

[0035] refer to Figure 1 ~ Figure 3 , a wrist reference bone segmentation method, comprising the following steps:

[0036] Step 1: Extraction and processing of the image of the reference bone feature region of the wrist;

[0037] Step 2: Training and generating an adaptive extraction model referring to the bone feature region;

[0038] Step 3: Adaptive extraction of wrist reference bone feature region.

[0039] The process of step 1 is as follows:

[0040] 3.1) Use the tool software LabelImg to mark 996 wrist X-ray films for training and learning of the feature region adaptive extraction model, including 836 training sets and 160 test sets. Use tool software to mark the coordinates of the upper left corner and the lower right corner of the feature area of ​​the reference bone. The principle of determining the size of the feature area is ...

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

A method for adaptively extracting reference bone feature regions of the wrist, comprising the following steps: step 1: extracting and processing images of reference bone feature regions; step 2: training and generating an adaptive extraction model for reference bone feature regions; step 3: referring to bone feature regions Adaptive extraction of feature regions. The present invention accurately extracts the characteristic region of the reference bone of the wrist through the self-adaptive extraction method of the characteristic region; on the basis of ensuring the integrity of the characteristic information of the reference bone, the interference of peripheral bone blocks and muscle tissues is reduced. The invention has strong universality to all reference bones, and is of great significance to the automatic identification of bone age and the evaluation of bone age by clinicians.

Description

technical field [0001] The invention relates to a method for extracting a wrist reference bone feature region. Background technique [0002] The method of calculating skeletal age by evaluating the maturity level of the reference bone and combining all the reference bone maturity levels is the most common bone age calculation method in the medical field. At the same time, the deviation of the bone age value calculated by the scoring method is small. Whether the clinician evaluates the maturity level of the reference bone or uses artificial intelligence to evaluate the maturity level of the reference bone, due to the irregular shape of the reference bone in the wrist in the X-ray film, the contrast between the reference bone and the surrounding muscle tissue is not high. When it is larger, the reference bone will fuse with other surrounding bone blocks, which makes it more difficult for experts to evaluate the maturity level of the reference bone, especially for artificial in...

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): G06V10/46G06N3/04G06N3/08G06T7/00G06T7/11
CPCG06T7/0012G06T7/11G06N3/084G06T2207/20081G06T2207/20084G06T2207/10116G06T2207/20004G06T2207/30008G06V10/462G06N3/044
Inventor 丁维龙丁潇毛科技万臧鑫
Owner ZHEJIANG UNIV OF TECH