Colorectal cancer lymph node metastasis identification method based on texture and morphological characteristics
A morphological feature, lymph node metastasis technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as non-uniqueness, volume thresholds do not form a unified conclusion, etc., and achieve the effect of high versatility
Inactive Publication Date: 2021-02-02
上海导萃智能科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The standard for lymph node metastasis is not unique. Routine imaging examinations use morphology as the criterion for judging lymph node metastasis, but this examination itself has great limitations. For example, some judgments use volume as the standard, but the volume threshold has not been formed. unified conclusion
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.
[0033] refer to Figure 1-Figure 7 , the present invention discloses a method for identifying colorectal cancer lymph node metastasis based on texture and morphological features.
[0034] Such as figure 1 As shown, it is the algorithm frame diagram of the present invention, which can be divided into two parts: lesion area feature extraction and lymph node metastasis identification. In the lesion area feature extraction stage, the preprocessed image is acquired through rectangular label frame extraction, ROI segmentation and morphological processing operations. Image, thereby extracting texture feature values and constructing morphological features, the lymph node metastasis ide...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a colorectal cancer lymph node metastasis recognition method based on texture and morphological characteristics, and the method comprises the following steps: preprocessing ofan image, and obtaining a preprocessed image; carrying out feature extraction on the lesion area of the preprocessed image to obtain a morphological feature map; wherein the feature extraction comprises statistical feature extraction based on image texture and morphological feature construction based on deep learning; and classifying the morphological feature maps by using an SVM-based image classification method and a deep learning-based image classification method, and performing feature analysis to obtain important factors influencing lymph node metastasis. The invention is suitable for various medical PET images, provides a new idea for solving the lymph node metastasis identification problem in the field of medical images, and has the advantages of high versatility, high processing rate and certain feature interpretation capability.
Description
technical field [0001] The invention relates to the technical field of machine vision medical imaging, in particular to a method for identifying colorectal cancer lymph node metastasis based on texture and morphological features. Background technique [0002] Image processing technology is usually the core part of a visual system, and the feature extraction technology and image classification technology involved in the present invention are one of the most important research methods in the field of image processing. [0003] The type of cancer (such as lung, stomach, or colorectal) indicates where the cancer started, but as the disease progresses, cancer cells can spread to other parts of the body and grow into new tumors, a process called metastasis. Cancer cells can travel through the lymphatic system after breaking away from the original tumor, thus entering the lymph nodes. The appearance of cancer cells in the lymph nodes is a sign that the cancer has started to spread...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/00G06T7/12G06T7/13G06T7/136G06T7/194G06T7/90G06K9/62
CPCG06T7/0012G06T7/12G06T7/13G06T7/136G06T7/194G06T7/90G06T2207/20036G06T2207/20081G06T2207/30028G06T2207/30096G06F18/2411
Inventor 张文强李谨慎吕宏张睿王娟娟
Owner 上海导萃智能科技有限公司