Supercharge Your Innovation With Domain-Expert AI Agents!

Aorta CT image key point detection method and system based on three-dimensional reconstruction

A CT image and 3D reconstruction technology, applied in image data processing, 3D modeling, instruments, etc., can solve the problems of insufficient training accuracy, difficult regression, and long training time, so as to improve accuracy, reduce training difficulty, and solve gradient problems. disappearing effect

Pending Publication Date: 2022-04-12
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Problems such as small sample size of medical images, long training time, insufficient training accuracy and difficult regression still restrict the progress of medical image processing

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
  • Aorta CT image key point detection method and system based on three-dimensional reconstruction
  • Aorta CT image key point detection method and system based on three-dimensional reconstruction
  • Aorta CT image key point detection method and system based on three-dimensional reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] like figure 1 As shown, the present embodiment provides a method for detecting key points in aortic CT images based on three-dimensional reconstruction;

[0049] Mark the key points of the upper body image of the human body, and obtain the key point data set of the 3D aortic CT image. The key points are the sinus-tubular junction, the boundary point between the ascending aorta and the aortic arch, the boundary point between the aortic arch and the descending aorta, and the enlightenment position of the iliac artery; The key point datasets of 3D aortic CT images include single-point 3D datasets, 4-point 3D single-category datasets, and 4-point 3D 4-category datasets.

[0050] In this embodiment, the labeling of key points of the aorta is mainly performed by using 3D Slicer software. Use 3Dslicer software to mark the CT images of the upper body of the human body given by the hospital, and use the frame selection tool to frame the aorta part in each aorta image group cons...

Embodiment 2

[0093] Such as Figure 6 As shown, the present embodiment provides a schematic structural diagram of aortic CT image key point detection system based on three-dimensional reconstruction, including: a labeling module, a cutting and mapping module, a frame selection module, a training module and a reconstruction module;

[0094] Specifically, the labeling module, the cutting and mapping module, the frame selection module, the training module, and the reconstruction module are connected in sequence; among them, the labeling module is used to label the key points of the upper body image of the human body, and obtain the key point data set of the 3D aortic CT image. The points are the sinotubular junction, the boundary point between the ascending aorta and the aortic arch, the boundary point between the aortic arch and the descending aorta, and the position of the iliac artery; the cutting and mapping module is used to perform multi-scale cutting and mapping on the key point data se...

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 an aorta CT image key point detection method and system based on three-dimensional reconstruction, and the method comprises the steps: carrying out the key point labeling of an upper body image of a human body, and obtaining a three-dimensional aorta CT image key point data set; obtaining a two-dimensional aorta CT image key point data set through multi-scale cutting mapping; carrying out target aorta frame selection, and carrying out cutting to obtain a 0 / 1 heatmap and an offset map; the Vnet network is improved, the 0 / 1 heatmap and the offset graph are input into the improved Vnet network for training, and a key point circle on the multi-scale view is generated; and carrying out space geometry three-dimensional reconstruction to obtain three-dimensional coordinates of the key points, and completing aorta CT image key point detection. The method can effectively solve the problems that in the aorta CT image processing process, the medical image sample size is small, the training time is long, the training precision is insufficient, and the regression difficulty is large.

Description

technical field [0001] The invention belongs to the technical field of aortic CT image processing, in particular to a method and system for detecting key points of aortic CT images based on three-dimensional reconstruction. Background technique [0002] As one of the important means of medical research at present, medical image processing provides an extremely important basis for the acquisition of detailed information in tissue structure anatomy, clinical operation guidance planning, lesion analysis and pathological location. With the development of machine learning technology, medical image processing technology has become more and more prominent in medical research and even clinical diagnosis, and intelligent processing technology based on deep learning has also been widely used. [0003] At present, many methods of image processing and detection for medical imaging have been developed: region-based detection methods, traditional detection methods based on shape models, d...

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): G06T17/00G06K9/62G06V10/774G06V10/764
Inventor 张百海李浩天柴森春王昭洋崔灵果姚分喜
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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