Brain tumor MIB-1 index range detection method
A MIB-1, detection method technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problem of insufficient standardization of immunohistochemical techniques and quantification of results, and the detection results are susceptible to the subjective influence of the testing personnel, and cannot be guided. Formulate preoperative treatment plans and other issues to avoid subjective influences, avoid insufficient standardization, and reduce costs
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0046] like figure 1 A brain tumor MIB-1 index range detection method is shown, including the following steps:
[0047] S1 collects magnetic resonance images of brain tumor patients, and constructs image training samples of lesion areas;
[0048] In this step, the magnetic resonance image includes any one or several of the T1 weighted sequence, the T1 enhanced sequence, and the FLAIR sequence, and the specific acquisition method is as follows:
[0049] Transverse, coronal, or sagittal magnetic resonance images of glioma patients are acquired using a magnetic resonance scanner (eg, GE Healthcare, 1.5T), including T1-weighted, T1-enhanced, and FLAIR sequences. Among them, the imaging parameters of the T1 weighted sequence are preferably Repetition Time=1966.1ms, Echo Time=21.088ms, Inversion Time=750ms; the imaging parameters of the T1 enhanced sequence are preferably Repetition Time=1967.25ms, EchoTime=7.264ms, Inversion Time=750ms ; The imaging parameters of the FLAIR sequen...
Embodiment 2
[0246] Due to the high dimensionality of the image feature sample set in the lesion area, it may contain some redundant image features. On the one hand, these redundant image features may reduce the classification accuracy, and on the other hand, will greatly increase the computational cost of the support vector machine. Therefore, as an option, the image feature sample set of the lesion area can be optimized based on the discrete particle swarm algorithm to obtain an optimized image feature set of the lesion area; the parameters of the support vector machine model are determined according to the optimized feature set of the lesion area image, which can effectively reduce the image features. complexity.
[0247] In particle swarm optimization, each potential solution to an optimization problem can be imagined as a point in the search space, called a particle. The quality of the particle's current position is evaluated by the objective function, and the objective function calcu...
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