Kidney benign and malignant tumor classification method based on multi-view information cooperation

A classification method and technology for malignant tumors, applied in neural learning methods, image analysis, image data processing, etc., can solve problems such as lack and difficulty in identifying kidney tumors, and achieve the goal of improving accuracy and reducing false positive and false negative rates. Effect

Inactive Publication Date: 2020-06-12
ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this field, there is still a huge difficulty in the identificati

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Kidney benign and malignant tumor classification method based on multi-view information cooperation
  • Kidney benign and malignant tumor classification method based on multi-view information cooperation
  • Kidney benign and malignant tumor classification method based on multi-view information cooperation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below in conjunction with accompanying drawing, the present invention is specifically explained

[0029] The network structure of the classification method for benign and malignant renal tumors based on multi-view information collaboration in the present invention is as follows: figure 1 As shown, the specific steps are as follows:

[0030] Step 1) medical image preprocessing;

[0031] Each case of renal CT images consists of images from three perspectives: sagittal, coronal, and transverse planes. Perform data enhancement operations such as flipping, rotating, zooming, cropping, and translating one or more of the three kidney CT images collected at any viewing angle to improve the anti-interference and generalization capabilities of the model. Crop the image after data enhancement into a 224*224 pixel image, which is conducive to better learning of the model. Finally, 80% of the processed data is used as the training set of the neural network of the present inventio...

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

No PUM Login to view more

Abstract

The kidney benign and malignant tumor classification method based on multi-view information cooperation comprises the following steps: step 1) medical image preprocessing: performing data enhancementprocessing on images of three views of kidney CT; 2) constructing a multi-view convolution network sub-model for the image of each view; and 3) constructing a multi-view information collaborative convolutional neural network model, unifying the outputs of the sub-models of the three views to the same neuron classification layer, and finally inputting a Sigmoid function to obtain a classification result. A penalty function is added for false positive cases, and greater penalty is given to reduce the occurrence of false positive conditions; and 4) kidney tumor benign and malignant classification: inputting a kidney CT image to be detected into the multi-view information collaborative convolutional neural network model constructed in the step 3), and performing network output to obtain a benign and malignant result of the tumor. According to the method, the multi-view image information of different kidney tumors is combined and fully utilized, the accuracy of kidney tumor benign and malignant classification can be improved, and meanwhile, the problem of poor model generalization ability caused by insufficient neural network training data due to lack of case image data is avoided.

Description

technical field [0001] The invention relates to a method for classifying benign and malignant tumors of the kidney. [0002] technical background [0003] Kidney tumors are one of the ten most common malignant tumors in humans, accounting for about 3% to 5% of the tumor incidence. In recent years, the incidence of renal tumors all over the world is on the rise, especially renal cell carcinoma, which increases at a rate of 2% to 3% every 10 years. According to the statistics of the American Cancer Society in recent years, from 2017 to 2019, there were 63,990, 65,340, and 73,820 new patients with kidney tumors in the United States; 14,400, 14,970, and 14,770 new deaths were reported. According to the latest records of my country Cancer Registry Center, in 2015, there were 66,800 new patients with kidney cancer and 234,000 new deaths in China, and many studies have recorded that the incidence and mortality of kidney cancer in my country have been on the rise in recent years, se...

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
no application Login to view more
IPC IPC(8): G06K9/62G06N3/04G06N3/08G06T7/11
CPCG06T7/11G06N3/08G06T2207/10081G06T2207/30096G06N3/045G06F18/241
Inventor 张聚俞伦端周海林吴崇坚吕金城陈坚
Owner ZHEJIANG COLLEGE OF ZHEJIANG UNIV OF TECHOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products