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

Coronary cta image processing method and device based on deep learning

A technology of deep learning and processing methods, applied in the field of image processing, which can solve the problems of increasing the burden of reading images for doctors and increasing the amount of data

Active Publication Date: 2022-03-08
青岛美迪康数字工程有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, with the sharp increase in the resolution of imaging equipment, the amount of data has also increased sharply, which has increased the burden of reading images on doctors

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
  • Coronary cta image processing method and device based on deep learning
  • Coronary cta image processing method and device based on deep learning
  • Coronary cta image processing method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Embodiments of the present invention provide a method for processing coronary CTA images based on deep learning, such as figure 1 As shown, the processing method of the coronary CTA image based on deep learning comprises:

[0050] S101. Convert the CTA image sequence into a target NIFTI file.

[0051] Among them, the CTA image sequence is a coronary CT angiography image sequence, and the NIFTI file is a standard format of medical images, which can convert all the images in the sequence into one file and contain the element information of all images, which is convenient for data sharing.

[0052] Specifically, open-source medical image processing software can be used to convert the medical image data format, and convert the dicom sequence images into the NIFTI file format.

[0053] S102. Invoking a pre-trained mask image recognition model, using the mask image recognition model to recognize the target NIFTI file, to obtain a NIFTI file with mask information.

[0054]Sp...

Embodiment 2

[0099] An embodiment of the present invention provides a processing device for coronary CTA images based on deep learning. The processing device for coronary CTA images based on deep learning includes: a memory, a processor, and a processor stored in the memory and capable of being stored in the memory. a computer program running on a processor;

[0100] When the computer program is executed by the processor, the steps of the method for processing coronary CTA images based on deep learning as described in any one of the first embodiment are realized.

[0101] In the specific implementation process of the second embodiment, reference may be made to the first embodiment, which has corresponding technical effects.

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 present invention relates to a method and device for processing coronary CTA images based on deep learning. The method includes: converting a CTA image sequence into a target NIFTI file; calling a pre-trained mask image recognition model to identify the target NIFTI file, and The obtained NIFTI file with mask information is converted into a target mask image sequence; the sternum region in the CTA image sequence is removed according to the target mask image sequence to obtain the target image sequence; the target image sequence is based on volume rendering 3D reconstruction: extract the vascular area from the 3D model, project each point on the vascular area onto a 2D plane, and obtain the reconstructed image of the vascular straightened. The present invention introduces a deep learning method, uses a pre-trained mask image recognition model to remove the sternum area in the CTA image sequence, and realizes three-dimensional reconstruction of the image, greatly shortens the processing time of the CTA image and achieves higher recognition accuracy.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for processing coronary CTA images based on deep learning. Background technique [0002] Coronary angiography (CTA, CT Angiography) is an important method for auxiliary diagnosis of heart diseases. Accurately segmenting coronary vessels from CTA data can not only provide a quantitative description of the vascular structure, but also observe and compare the geometric changes of the blood vessels, which is beneficial to the disease. The diagnosis and treatment are of great significance. At present, with the sharp increase in the resolution of imaging equipment, the amount of data has also increased sharply, which has increased the burden of reading images on doctors. Therefore, with the help of computer-aided diagnosis technology, processing and analyzing cardiac images and then diagnosing cardiovascular diseases has become a research hotspot a...

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): G06T7/00G06T7/11G06T17/00G06T5/00G06T5/30G06N3/04G06N3/08A61B6/03A61B6/00
CPCG06T7/0012G06T7/11G06T17/00G06T5/30G06N3/08A61B6/032A61B6/504A61B6/5211G06T2207/10016G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30048G06T2207/30101G06N3/045G06T5/70
Inventor 赖永航陈栋栋袁鹏
Owner 青岛美迪康数字工程有限公司