Deep neural network-based X-ray film hand bone region of interest automatic extraction method

A technology of deep neural network and region of interest, which is applied in the field of region of interest extraction of X-ray images of human hand bones, can solve the problems of large error, low efficiency, and low precision, and achieve the effect of reducing error, improving efficiency, and reducing the risk of paralysis

Active Publication Date: 2018-04-03
浙江飞图影像科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the disadvantages of low efficiency, large error and low precision of the existing X-ray hand bone region of interest extraction methods, the present invention proposes an X-ray method based on deep neural network with high efficiency, small error and high precision. The method of automatically extracting the region of interest of the hand bone in the X-ray film can not only automatically obtain the hand bone area in the X-ray film, but also automatically remove noise and adjust the brightness

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
  • Deep neural network-based X-ray film hand bone region of interest automatic extraction method
  • Deep neural network-based X-ray film hand bone region of interest automatic extraction method
  • Deep neural network-based X-ray film hand bone region of interest automatic extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] refer to Figure 1 to Figure 4 , for the sampling work of Output1, it is mainly to sample pictures with text information through the sliding window, especially the large letter L. By training the model M1, the detection of whether there is text information in the picture can be almost 100% completed. When Output1 is input into the model, selective search is used to detect large letters as objects, and at the same time, a unified coverage strategy is adopted for other characters existing in the corners. This saves the time of sliding the window on the original large image, and can effectively remove text information.

[0049] The present invention normalizes the image to a uniform size after removing the text information, which will reduce the time complexity of subsequent acquisition of the marker mapping of the region of interest of the hand bone. For the ac...

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 deep neural network-based X-ray film hand bone region of interest automatic extraction method. The method comprises the steps of for an original hand bone X-ray film image, removing text embedded parts of black backgrounds on two sides of the image; performing brightening and denoising operations on the original hand bone X-ray film image in a unified way; sampling and training a model M1 to obtain a text-free hand bone X-ray film image Output2; for the Output2, normalizing the size to obtain Output3; sampling and training a model M2, and judging hand bones, backgrounds and intersection parts of the hand bones and the backgrounds in the Output3; based on the model M2, judging an image sliding window in the Output3, and according to a judgment value, obtaining a hand bone marker mapping graph Output4; based on the Output3 and the Output4, obtaining an image Output5 only with the hand bones; and optimizing the Output5 to obtain a final hand bone region of interest.

Description

technical field [0001] The present invention relates to the fields of medical image analysis and machine learning, in particular to a method for extracting regions of interest from X-ray images of human hand bones, which belongs to the field of medical image analysis based on deep learning. Background technique [0002] Skeletal age, referred to as bone age, is determined by the degree of bone calcification in children. Bone age can more accurately reflect the developmental level of a person at each age stage from birth to full maturity. Not only that, but also in the analysis and diagnosis of endocrine diseases, developmental disorders, nutritional disorders, genetic diseases and metabolic diseases, bone age has important functions. important role. Radiologists measure a child's bone age by comparing x-rays of the child's hand to a standard for their age. The technology is stable and has been around for decades. With the improvement of parents' health awareness, the numb...

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): G06T7/00G06T7/11G06T7/136G06T7/194G06K9/32
CPCG06T7/0012G06T7/11G06T7/136G06T7/194G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30008G06V10/25
Inventor 郝鹏翼陈易京尤堃吴福理黄玉娇白琮
Owner 浙江飞图影像科技有限公司
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