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

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...

AI Technical Summary

Problems solved by technology

However, in this field, there is still a huge difficulty in the identification of kidney tumors due to the lack of a large number of training data sets.

Images