OCT (Optical Coherence Tomography) image processing device for qualitative and boundary positioning in brain tumor operation
An image processing device and image processing technology, applied in the field of tumor imaging, can solve the problems of lack of OCT technology qualitative and boundary positioning, tumor tissue and necrotic tissue hindering the popularization and application of OCT, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] OCT image database construction
[0046] The image of the OCT image database is an image feature extraction module, the classification qualitative module, and the boundary positioning module processed by the OCT image processing system, and the depth fusion of multiple feature is performed by the classification qualitative module;
[0047] The comprehensiveness of the OCT image database also includes comparison the OCT image of different tissues to its histopathology;
[0048] The OCT image database is built, and includes the use of computer technology for feature extraction, classification qualitative, and boundary positioning of OCT image database;
[0049] Use Zeiss's 1300nm-band sweep frequency OCT system to collect two-dimensional / three-dimensional OCT images of animal living brain tissue and intraoperative human brain tissue, compare the OCT image of different tissues with its histopathology, as A portion of the OCT image database, while utilizing an OCT image pre-p...
Embodiment 2
[0051] OCT image characteristic extraction
[0052] The OCT image pre-processing module of the image feature extraction module is pre-processed from the enhanced contrast, image denoising and image registration;
[0053] The texture characteristics and depth features of the OCT image after the OCT image pre-processed are multi-feature extracted, the texture characteristics with the pre-processed OCT image as extraction object, extracts 5-dimensional straight diagram characteristics , 92 dimensional gray symbiotic matrix characteristics, 44 dimensional gray run length matrix characteristics; by extracting the ROI region grayscale matrix, calculating the grayscale histogram of the image, the extracted texture characteristic has a mean, variance, silakeity, peak and energy;
[0054] The mean calculation formula is as follows:
[0055]
[0056] Where H i For the pixel frequency of the grayscale value I, g max For the maximum gray value of the image;
[0057] Variance calculation for...
Embodiment 3
[0074] Subrigration of OCT images extracted with multiple feature
[0075] The classification qualitative module performs deep fusion of the above-mentioned multi-characterization, based on the SVM classifier core function mechanism, input depth features and texture features in multiple core functions and their multiple parameters, find the most suitable texture characteristics and depth features, respectively. The core function and parameter settings, and the weight of the respective nuclear functions, and then fuse the depth feature kernel function and the texture feature kernel function together to realize the multiple feature to perform multi-core function classification of multi-character species by the SVM classifier;
[0076] The image of multi-core function classification using the SVM classifier is characterized by comparing the OCT image database, and the OCT image database contrasts the multi-characterization of texture characteristics, depth features, and fusion;
[00...
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