Image processing method applied to surgical navigation
A technique of surgical navigation and image processing, applied in the field of image processing applied to surgical navigation, can solve the problems of low contrast of lesion tissue, limited application scope of surgical navigation system, inability of surgical navigation system to effectively implement surgical navigation, etc. sexual effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] Such as figure 1 As shown, the present invention provides an image processing method applied to surgical navigation,
[0053] S10, acquiring the subject image;
[0054] S20, image registration: if the acquired images to be tested include multimodal images of CT images and / or MR images, perform multimodal image registration;
[0055] S30, Image Segmentation: Segment the voxels of the acquired image according to the background, blood vessels, nerves, bones, lesions, and organs where the lesions are located, and mark them as L in sequence b , L v , L n , L s , L f and L t ;
[0056] S40, feature extraction and processing: respectively extract the features of the background, blood vessels, nerves, bones, lesions, and organs where the lesions are located, and perform feature vector preprocessing;
[0057] S50, region of interest analysis: calculating basic features, geometric features, shape features, surface shape, texture, statistical features, topological features...
Embodiment approach
[0064] As a preferred embodiment of the present invention, feature extraction, such as figure 2 shown, including the following steps:
[0065] S41, selecting a neighborhood range whose voxel size is R in the multimodal image;
[0066] S42, calculate the histogram feature set of voxels in the neighborhood range R;
[0067] S43, calculating the gray level co-occurrence matrix feature set of voxels in the neighborhood range R;
[0068] S44, calculating the gray run length matrix feature set of the voxels in the neighborhood range R;
[0069] S45. Calculate a set of gray-scale region size matrices of voxels in the neighborhood range R.
[0070] In this embodiment, the histogram feature set includes: the mean and standard deviation of the Gaussian curve fitted by the least square algorithm, skewness, peak value, uniformity, entropy, grayscale variability, size region variability, and the 2.5th in the histogram HU at the 1st percentile, HU at the 25th percentile in the histogra...
Embodiment 2
[0083] On the basis of Example 1, this embodiment provides a preferred implementation mode, and before obtaining the subject image, it also includes steps:
[0084] S70. Establish an image database, and perform image registration on the images in the image database.
[0085] In this embodiment, the way of establishing the image database can be based on the tree structure, and the image storage directory can be established sequentially according to the modality and time point. Manage the storage directory according to the mode form and time point: the image data of the same subject is stored in the same directory; if the subject has images of multiple different modalities, create multiple subdirectories in the subject’s directory, To store the images of different modalities separately; if there are multiple images of different time points in the images of a certain modality of the subject, then create multiple subdirectories under the directory of the modality, and store the im...
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