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

Bone shadow suppression method and device based on neural network, equipment and storage medium

A technology of neural network and neural network model, applied in the field of neural network-based bone shadow suppression methods, devices, equipment and readable storage media, can solve the problem of DR equipment not having DES function, reducing the service life of X-ray tubes, increasing Patient radiation dose and other issues, to achieve the effect of enhancing the performance of network details, clear texture details, and reducing radiation dose

Active Publication Date: 2021-03-19
万里云医疗信息科技(北京)有限公司
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the vast majority of DR equipment in clinical use does not have DES function, and its application and popularization rate are not high
In addition, compared with ordinary X-ray equipment, X-ray DES equipment detection requires the use of additional equipment, which may reduce the service life of the X-ray tube; moreover, DES imaging requires two exposures of X-rays, which not only increases the patient's acceptance The radiation dose also makes the imaging quality vulnerable to the movement of human tissues such as the patient's respiration and heart beat, resulting in motion artifacts in the acquired soft tissue images and bone images

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 shadow suppression method and device based on neural network, equipment and storage medium
  • Bone shadow suppression method and device based on neural network, equipment and storage medium
  • Bone shadow suppression method and device based on neural network, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0063] At present, the main problem of the regression prediction model used for chest radiographic bone shadow suppression is that it needs to perform complex contrast normalization processing on the chest radiograph, extract effective features from the chest radiograph image and optimize the parameters of the regression prediction model to Guaranteed prediction accuracy.

[0064] In the embodiment of this application, ribs are regarded as noise information in the image, and the image denoising method is used to complete the task of rib bone shadow suppression. The deep convolutional network is used as the basic model, and various strategies are analyzed and...

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 relates to a bone shadow suppression method, device and equipment based on a neural network, and a readable storage medium, and belongs to the technical field of medical images, and themethod comprises the steps: constructing a neural network model through a ResUnet network; training the neural network model to obtain a trained neural network model; obtaining a DICOM image to be suppressed of the human lung; preprocessing the DICOM image to be suppressed; and inputting the preprocessed DICOM image to be suppressed into the trained neural network model for bone shadow suppression, and outputting the DICOM image after bone shadow suppression. According to the invention, the influence of human tissue motion on DES imaging quality and the radiation dose accepted by a patient canbe reduced.

Description

technical field [0001] The present application relates to the technical field of medical imaging, in particular to a neural network-based bone shadow suppression method, device, equipment and readable storage medium. Background technique [0002] With the development of digital radiography (Digital Radiography, DR for short) and computer radiography (Computed Radiography, CR for short) equipment and technology, X-ray dual energy subtraction technology (Dual Energy Subtraction, DES for short) has been able to separate the Characteristic images that reflect tissue components—Soft-tissue Image and Bone Image. DES equipment uses high and low X-rays with two different energies (such as 120kV and 60kV) to take two images, and uses the phenomenon that tissues have different attenuation coefficients of different energy X-rays to perform weighted subtraction processing, which can separate tissues with different attenuation coefficients. Obtain soft tissue and bone images. [0003] ...

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
IPC IPC(8): G06T5/00G06T5/50G06T7/00G06T7/11G06T7/507G06N3/04G06N3/08
CPCG06T5/50G06T7/0012G06T7/11G06T7/507G06N3/04G06N3/084G06T2207/10116G06T2207/20081G06T2207/20104G06T2207/20221G06T2207/30061G06T5/90
Inventor 任大伟罗飞黄家祥王晓晖
Owner 万里云医疗信息科技(北京)有限公司