Computer aided pulmonary nodule classification method based on migratable multi-model integration

Abstract

The invention discloses a computer-aided pulmonary nodule classification method based on migratable multi-model integration to solve the technical problem of low accuracy of an existing pulmonary nodule classification method. The technical scheme includes the steps of training three pre-trained deep convolutional neutral networks (Pre-trained DCNN), describing the textural heterogeneity, shape heterogeneity and global characteristics of pulmonary nodules respectively, performing weighted average for results of the deep convolutional neutral networks, and subjecting the weight of each network to adaptive learning through an error back propagation mechanism so as to improve the accuracy of the pulmonary nodule classification method, wherein, the Pre-trained DCNN migrates the good image characterization capability of the deep convolutional neutral network on a large data set onto a pulmonary nodule classification task so that the training performance of the deep convolutional neutral networks on small pulmonary nodule data is effectively improved. The invention overcomes the technical problem of low accuracy of a classification method based on single type of information, and the accuracy rate can be up to 93%.

Description

technical field [0001] The invention relates to a pulmonary nodule classification method, in particular to a computer-aided pulmonary nodule classification method based on transferable multi-model integration. Background technique [0002] The traditional benign and malignant classification technology of pulmonary nodules based on CT images can generally be divided into three parts: pulmonary nodule segmentation, feature extraction and benign and malignant classification of pulmonary nodules. The above methods rely on the pre-segmentation of pulmonary nodules. Many current segmentation methods rely on the initialization of algorithms, such as region growing algorithms, level set algorithms, etc. Different initializations will have different effects on the final segmentation results, therefore, the features obtained by using such segmentation results are usually inaccurate. [0003] The document "Application Publication No. CN 104700118 A Chinese Invention Patent" discloses...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiency of poor accuracy rate of existing pulmonary nodule classification methods, the pre

Images