Tumor interstitial ratio judgment method and system based on image processing algorithm
A tumor stroma and image processing technology, applied in the field of medical image processing, can solve problems such as large uncertainties
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0066] A method for judging the tumor-stroma ratio based on an image processing algorithm according to the present invention includes:
[0067] Step M1: Read HE immunohistochemical images of tumor pathological sections;
[0068] Step M2: Select an image whose average gray value and blur degree of the image are within a preset range;
[0069] Step M3: Preprocessing the selected image based on the image preprocessing algorithm to obtain the preprocessed image;
[0070] Step M4: Segment the preprocessed image;
[0071] Step M5: Obtain and mark the segmentation results, and calculate the mass ratio between tumors.
[0072] Specifically, the step M3 includes:
[0073] Step M3.1: Perform grayscale processing on the HE immunohistochemical image, and normalize the image data;
[0074] Step M3.2: After the image is normalized, the image is denoised for the first time by median filtering, which can better eliminate noise and make each area of the image smooth;
[0075] Step M3.3:...
Embodiment 2
[0105] Embodiment 2 is a modification of embodiment 1
[0106] The purpose of the present invention is to provide a reliable solution for calculating the ratio of tumor cells to the interstitium, by dividing the interstitial part and the substantial part of the pathological HE immunohistochemical image of tumor cells, and calculating the ratio of each to the total area of the image to obtain these data. This solution is more efficient and accurate than the traditional method used by doctors to calculate the ratio of tumor to stroma. At the same time, the system comes with a set of interactive GUI interface, which is user-friendly.
[0107] The present invention provides two segmentation schemes, both of which require four preprocessing steps on the image. First of all, we need to grayscale the image for two reasons: 1. The tumor-stroma ratio image is an RGB image consisting of three color channels (in Matlab, it is expressed as a three-channel matrix), which is inconvenient...
Embodiment 3
[0144] Embodiment 3 is a modification of embodiment 1 and / or embodiment 2
[0145] figure 1 It is a flow chart of the method of the present invention.
[0146] figure 2 It is the original image of the tumor image, the color distribution of the image is uneven, and it is greatly affected by noise. Therefore, it is necessary to properly preprocess the image.
[0147] Step 1: Perform grayscale processing on the original image. Grayscale processing is to scale the grayscale values of all pixels in the image between [0,1]. It is a normalized process, which is convenient. The calculation of the data, and the subsequent preprocessing steps, whether it is median filtering or histogram equalization, require the gray value of the image to be controlled between [0,1]. This step is the premise of the algorithm.
[0148] Step two, such as image 3 As shown, median filtering is performed on the grayscaled image for the first noise reduction. Median filtering (Median filtering) is an ...
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