Method for real-time superposition of three-dimensional medical image and patient and operation auxiliary system
A medical imaging and 3D imaging technology, applied in surgical navigation systems, surgery, medical science, etc., can solve problems such as inaccurate matching between 3D medical images and patients' bodies, frequent switching of sight lines, etc., to reduce surgical risks, improve matching speed, The effect of high coincidence matching accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0080] Attached below figure 1 The flow chart of the method for real-time overlapping of three-dimensional medical images and patients illustrates this embodiment 1:
[0081] A method for real-time overlapping of a three-dimensional medical image and a patient, the method being:
[0082] Convert the patient's CT sequence image or MRI sequence image into an overall point cloud, and reconstruct the 3D model of the patient's CT sequence image or MRI sequence image to form a 3D medical image;
[0083] Obtaining an image corresponding to a CT sequence image or a nuclear magnetic sequence image on the patient's body, the image is a partial image of the patient's body, and converting the partial image into a local point cloud;
[0084] The overall point cloud and the local point cloud are registered using the Super-4PCS algorithm, and the spatial coordinates of the overall point cloud and the spatial coordinates of the local point cloud are determined to accurately coincide in the s...
Embodiment 2
[0088] According to the method for real-time overlapping of three-dimensional medical images and patients described in embodiment 1, the extraction method of the whole point cloud of the present invention is specifically described,
[0089] The extraction method of the whole point cloud is:
[0090] Select an appropriate threshold in the patient's CT sequence images or MRI sequence images;
[0091] Since there is a significant difference in the pixel gray value of the target area and the background area of the patient's CT image or nuclear magnetic image, so the present invention uses a threshold segmentation algorithm to segment the patient's CT image or nuclear magnetic image, and the selection process of the appropriate threshold is:
[0092] (1) Select a pre-estimated threshold T according to the pixel gray value of the target area and the background area in the patient's CT image or MRI image;
[0093] (2) Segment the CT image or MRI image of the patient with the thres...
Embodiment 3
[0102] According to the method for real-time overlapping of the three-dimensional medical image and the patient described in embodiment 1, the method for obtaining the local point cloud is:
[0103] Find the characteristic region corresponding to the CT sequence image or nuclear magnetic sequence image obtained before applying the method on the patient's body, use a depth image acquisition device to obtain continuous depth images of the characteristic region, and convert the continuous depth of the characteristic region Images are converted into local point clouds using threshold segmentation.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com