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

A machine learning-based cutting method for regions of interest in wrist bones

A region of interest and machine learning technology, applied to instruments, computer components, computing, etc., can solve the problem that the size of the cutting frame cannot be uniformly fixed, and achieve the effect of improving the recognition rate

Active Publication Date: 2022-06-28
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

[0004] The purpose of the present invention is to overcome the problem that the size of the cutting frame required by different heights and ages of the wrist bone medical image cannot be uniformly fixed, and to segment the wrist bone medical image based on machine learning, and to provide an automatic cutting method for bone age image size self-adaptation

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

[0015] This embodiment provides a method for cutting a wrist bone region of interest based on machine learning, including the following steps:

[0016] 1) Select a batch of wrist bone samples of different ages and heights according to the actual situation, and for each sample piece, the geometric center points of the 14 bones targeted by the CHN bone age assessment method are calibrated; the 14 bones are respectively For: radius, palm 1, palm 3, palm 5, proximal 1, proximal 3, proximal 5, medial 3, medial 5, distal 1, distal 3, distal 5, capitulum, hamate;

[0017] 2) For each sample piece, based on the geometric center point demarcated in the previous step, further demarcate a rectangular cutting area with appropriate length and width for each bone that can completely encapsulate the picture information required for bone age grade identification, and complete the next step. The data set used for the machine learning of the steps is made;

[0018] 3) Using the age and height ...

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 for cutting a wrist bone interest region based on machine learning. The invention uses the machine learning method to segment medical images, and achieves better results through the combination of center point cutting and self-adaptive cutting frame size. The method of the present invention makes a more precise cutting and extracts features for each wrist bone picture on the premise of ensuring that each individual is independent in size. The invention can generate an adaptive cutting frame for any height and age, and provides data support for more accurate determination of wrist bone grade. The method of the present invention can be applied to feature region cutting in the field of image recognition, which greatly improves the recognition rate of the deep learning network.

Description

technical field [0001] The present invention relates to the technical field of self-adaptive cutting of medical pictures, in particular, to a method for cutting a wrist bone interest region based on machine learning. Background technique [0002] Now deep learning has a very broad prospect in image recognition, natural language processing, speech recognition and other fields. With the wide application of deep learning technology in medical images, automatic bone age assessment has also become a hot topic. [0003] The maturity ensemble averaging method based on the automatic weighting of variance analysis, namely the CHN method, is an evaluation method for Chinese wrist bones. This method makes a corresponding grade evaluation for 14 wrist bones. Combined with deep learning network, the data set of 14 wrist bone medical images is learned to achieve the purpose of automatically judging bone age. Due to the uneven size of the 14 bones in the wrist bone age images of differen...

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): G06V10/26G06V10/25G06V10/82
Inventor 毛科技丁维龙陈立建周贤年丁潇
Owner 浙江康体汇科技有限公司
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