Bone age mark identification assessment method and system based on deep learning and image omics

A technology of deep learning and radiomics, applied in medical informatics, character and pattern recognition, instruments for radiological diagnosis, etc., can solve the problem of small amount of training data

Active Publication Date: 2018-01-16
WINNING HEALTH TECHNOLOGY GROUP CO LTD
View PDF2 Cites 61 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the problem of less training data in the prior art, and obtain a better accuracy rate on the basis of improving the bone age evaluation speed, but still need to learn in the whole image Intermediate features are used to complete bone age prediction. Due to the small amount of data, the uncertainty of the feature extraction area and the large difference in clinical methods, there are still shortcomings in the evaluation accuracy, speed and generalization ability. and radiomics bone age marker recognition and evaluation method and system

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
  • Bone age mark identification assessment method and system based on deep learning and image omics
  • Bone age mark identification assessment method and system based on deep learning and image omics
  • Bone age mark identification assessment method and system based on deep learning and image omics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Such as figure 1 As shown, the bone age marking method based on deep learning and radiomics of this embodiment includes:

[0068] 101. Input the wrist bone image data to be marked into the RCNN-based BoneNet model, the BoneNet model includes a ResNet network structure, and the ResNet network structure is also used for migration learning of the BoneNet model;

[0069] In practice, in view of right-handed people (right-handed type), the development of the bones of the right hand will be more mature than that of the left hand, on the contrary, for left-handed people (left-handed type), the bone development of the left hand will be more mature than that of the opposite side. Therefore, here the bone image data of the wrist, the right-handed type uses the X-ray of the left hand, and vice versa. In addition, the bone image data of the wrist conforms to the DICOM (Digital Imaging and Communications in Medicine, medical digital imaging and communication) image data format;

...

Embodiment 2

[0083] like figure 2 As shown, the bone age recognition method based on deep learning and radiomics in this embodiment includes:

[0084] 201. Obtain the wrist bone image data to be identified and the corresponding inspection report, the inspection report including the type and quantity of ossification centers;

[0085] Further, clinical information corresponding to the wrist bone image data to be identified is also obtained, and the clinical information includes age and gender;

[0086] 202. Use the BoneNet model of the bone age marking method based on deep learning and radiomics as described in Example 1 to mark the bone age feature region of the wrist bone image data to be identified;

[0087] Further, the BoneNet model also includes a bone age assessment classifier, the bone age assessment classifier uses a stacking ensemble method, the stacking ensemble method includes random forest, KNN, boosting algorithm, the random forest, the KNN, the boosting Algorithms are used ...

Embodiment 3

[0096] like image 3 As shown, the bone age assessment method based on deep learning and radiomics of this embodiment includes:

[0097] 301. Obtain the bone image data of the wrist to be evaluated and corresponding clinical information, where the clinical information includes age and gender;

[0098] 302. Use the BoneNet model of the bone age recognition method based on deep learning and radiomics as described in Example 2 to locate and classify the wrist to be evaluated according to the bone image data of the wrist to be evaluated and corresponding clinical information The bone age characteristic area and the corresponding ossification center and bone quantity of the internal bone image data;

[0099] 303. Output the bone age data corresponding to the bone image data of the wrist to be evaluated, the bone age data includes the bone age characteristic area, the corresponding ossification center, the number of bones, and the bone age evaluation value, and the bone age evaluat...

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 bone age mark identification assessment method and system based on deep learning and image omics. The bone age mark identification method includes the steps: performing preprocessing of window adjusting, alignment and standardization on the wrist bone image; using a bounding box to mark the bone age characteristic areas and mark the coordinates, wherein the bone age characteristic areas include a metacarphphalangeal group and a brachidium group according with a TW3 method; according to the requirement, performing augmentation processing, and inputting the wrist bone image data to a convolutional neural network of the area based on ResNet-101 to perform multi-task (positioning, classification and assessment) training at the same time; and based on the bone age characteristic areas, combining with the clinic information (demographic characteristics and inspection reports) to further train and improve the bone age assessment speed and accuracy. The bone age markidentification assessment method and system based on deep learning and image omics firstly utilize a small number of marked samples to perform preliminary training on the bone age model, and utilize the model with relatively higher positioning detection accuracy to automatically mark a large number of samples so as to realize automatic positioning, classification and bone age assessment of the bone age characteristic areas.

Description

technical field [0001] The present invention relates to the field of medical image processing, in particular to a bone age marker recognition and evaluation method and system based on deep learning and radiomics. Background technique [0002] In the early days, doctors generally obtained bone age information by interpreting and scoring X-rays of human wrists. Usually, scoring methods such as counting method, atlas method, scoring method and computer bone age scoring system were used. The most commonly used is G-P Atlas method (bone age atlas made by Greulich and Pyle, referred to as G-P atlas). In addition, according to bone age to predict adult height, there are usually B-P method (the percentage method of predicting adult height proposed by Bayley and Pinneau), CHN method (Chinese wrist bone development standard), TW3 method (bone age scoring method proposed by Tanner and Whitehouse) , referred to as TW law, now the third revision) and so on. These methods mainly have th...

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): G16H50/20G16H15/00G06K9/62A61B6/00
Inventor 陈旭刘宁赵大平杨秀军王乾兰钧潘志军岁波洪平宋晓霞
Owner WINNING HEALTH TECHNOLOGY GROUP CO LTD
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