Supercharge Your Innovation With Domain-Expert AI Agents!

A method and device for detecting bone regions in images

A bone and area technology, applied in the field of detecting bone areas in images, can solve the problems of low efficiency and large impact on the accuracy of bone areas.

Active Publication Date: 2022-04-12
HANGZHOU YITU MEDIAL TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method and device for detecting bone regions in an image, which are used to solve the problem that the accuracy of the bone region is greatly affected by human subjective factors and the efficiency is low due to manual detection of the bone region in the image in the prior art. technical issues

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
  • A method and device for detecting bone regions in images
  • A method and device for detecting bone regions in images
  • A method and device for detecting bone regions in images

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0079] In a specific implementation, for the first image intercepted from any frame of 2D image, the first image can be input into the first convolutional neural network model to output the confidence that each pixel in the first image belongs to the bone region, Furthermore, an area composed of one or more pixels whose confidence degree of the pixel in the first image belongs to the bone area is greater than the second threshold can be used as the bone area in the frame of 2D image; for example, after each pixel is determined After the confidence of belonging to the bone region, you can keep the pixels on the first image whose confidence is greater than or equal to the second threshold, and delete the pixels on the first image whose confidence is less than the second threshold. In this way, the retained pixels consist of The area of ​​is the bone area in the frame of 2D image.

[0080] In this example, by detecting the confidence that each pixel point on the first image belon...

example 2

[0082] In specific implementation, for the first image intercepted from any frame of 2D image, the first image can be input to the second convolutional neural network model to output the key points of the bone area in the first image, each key The point may be a point on the edge of the bone area; further, each key point of the bone area in the first image may be connected, and the area surrounded by each key point may be used as the bone area on the frame of 2D image.

[0083] In this example, by detecting the edge key points of the bone area on each frame of 2D image, the area surrounded by the connected edge key points can be directly used as the target bone area. This detection method has fast processing speed and high detection efficiency.

[0084] It should be noted that the training methods of the first convolutional neural network model in Example 1 and the second convolutional neural network model in Example 2 can be implemented with reference to the third convolutiona...

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 embodiment of the present invention discloses a method and device for detecting bone regions in an image, which acquires multiple frames of continuous 2D images, detects the center of the bone region in each frame of 2D images, obtains the detected center of the bone region in the frame of 2D images, and uses Predict the center of the bone region in the frame of 2D images from the detected center of the bone region in at least two frames of 2D images other than the frame of 2D image, obtain the predicted center of the bone region in the frame of 2D image, and determine based on the predicted center and the detected center The center of the bone region in the frame of 2D image, and the bone region in the frame of 2D image is obtained based on the center of the frame of 2D image. The bone area in the 2D image is quickly determined through the center of the bone area in the 2D image, without manual judgment based on the 2D image, and the efficiency of detecting the bone area in the 2D image and the accuracy of the bone area are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of machine learning, and in particular to a method and device for detecting bone regions in an image. Background technique [0002] With the development of modern medical imaging technology, various medical imaging devices are constantly emerging, such as X-ray photography equipment, computed tomography (Computed Tomography, CT) equipment, nuclear magnetic resonance imaging (Nuclear Magnetic Resonance Imaging, NMRI) equipment and so on. These medical imaging devices can collect 2-dimensional (dimensional, D) images (cross-sectional images) of various parts of the human body, and can also generate 3D images of various parts of the human body. After the medical imaging equipment collects the image, it usually involves the detection of the bone area from the image. By pre-determining the bone area, it is convenient to formulate a treatment plan. [0003] In the prior art, the bone area 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): G06T7/00
CPCG06T7/0012G06T2207/10081G06T2207/30008G06T2207/20081G06T2207/20084
Inventor 倪浩石磊魏子昆华铱炜柏慧屏
Owner HANGZHOU YITU MEDIAL TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com