Pulmonary nodule benignity and malignancy detection method based on feature-fusion convolutional neural network

Abstract

The invention discloses a pulmonary nodule benignity and malignancy detection method based on feature-fusion convolutional neural network. According to the method, first a position area of a pulmonarynodule needs to be drawn in a lung CT image according to marking of an expert, then an area of interest of the pulmonary nodule is segmented according to the position information, and images having the same size and only containing the pulmonary nodule are obtained; next, HOG features and LBP features of the pulmonary nodule images are extracted to obtain corresponding visual feature maps; and then the pulmonary nodule images, LBP feature graph and HOG feature map are used as input of a convolutional neural network to carry out convolution operation, image features are further extracted, andfinally, the probability that the pulmonary nodule is benign or malignant is obtained through classification. In the process of feature extraction, since what LBP and HOG extract is local information,what the convolutional neural network extracts is global information, traditional features and convolutional neural network (CNN) features are fused to carry out a pulmonary nodule benignity and malignancy analysis, a higher accuracy rate can be obtained, and better robustness is achieved.

Description

technical field [0001] The invention provides a method for detecting benign and malignant pulmonary nodules based on a feature fusion convolutional neural network. Background technique [0002] Lung cancer is currently the malignant tumor disease with the highest mortality rate in the world, accounting for 27% of all cancer mortality. According to the statistics of SEER in the United States, when lung cancer is confirmed, the tumors of most patients have spread and metastasized, and no more than 15% of patients survive for more than 5 years after confirmation. A key issue in the diagnosis of pulmonary nodular lesions is the correct detection and accurate identification of pulmonary nodules. After detection, diagnosis and confirmation of pulmonary nodules, benign and malignant lesions can be effectively judged. Clinically, it is difficult to detect and diagnose pulmonary nodules. At present, the rate of misjudgment and missed judgment of pulmonary nodules is still high. Usi...

AI Technical Summary

Problems solved by technology

Compared with the traditional self-generated neural network and BP algorithm, it has higher accuracy, but it needs multiple optimizations, which will lead to long running time and high time complexity.

Images