Cancer diagnosis system and method based on breast molybdenum target calcification characteristics
A technology of cancer diagnosis and mammography, which is applied in the field of medical image processing, can solve the problems of unsatisfactory test sample results and achieve the effect of improving the accuracy of cancer diagnosis
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] like figure 1As shown, this embodiment provides a cancer diagnosis system based on mammography calcification features, including an image preprocessing module for performing image enhancement and lesion detection on mammography images to obtain calcified lesion areas; for calcified lesions The feature extraction module extracts traditional features and deep features of the region, performs typical correlation analysis on traditional features and deep features, and screens out features that are not closely related to traditional features in deep features; for filtered deep features, training support vectors through samples A feature classification module for machine classification of new calcified lesions.
[0044] Wherein, the image preprocessing module includes an image intensifier that highlights the characteristics of the calcified lesion area by performing contrast enhancement and morphological transformation on the mammography image; a wavelet transform processor f...
Embodiment 2
[0048] This embodiment provides a method for diagnosing cancer based on mammogram calcification features, the flow chart of the method is as follows figure 2 shown, including the following steps:
[0049] Step 1: Obtain a mammography image set (P 1 ,P 2 ,...P n ) and its benign and malignant labels (l 1 , l 2 ,...l n ); among them, n>100, l i ∈{-1,1};
[0050] Step 2: Carry out enhancement processing to the data in the mammography X-ray image set respectively, and perform binarization to segment the calcified lesion area (I 1 , I 2 ,...I n ), the flow chart is as image 3 Shown; the specific process is:
[0051] Step 2.1: Mammography image set (P 1 ,P 2 ,...P n ) for contrast enhancement, and then filter out its low-frequency part through db4.7 wavelet, retain its high-frequency part, and obtain the image set after contrast enhancement and wavelet reconstruction (Z 1 ,Z 2 ,...,Z n );
[0052] Step 2.2: Multiply the adaptive threshold of the Otsu method by th...
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