Deep model and shallow model decision fusion-based pulmonary nodule CT image automatic classification method

Abstract

The invention relates to a deep model and shallow model decision fusion-based pulmonary nodule CT image automatic classification method. Deep convolutional neural network-based features and visual features describing pulmonary nodule textures and shapes are extracted. Three classifiers are trained for the three different features, and results of all the classifiers are subjected to weighted averaging to obtain a final classification result. Therefore, the innovation of a CT image-based pulmonary nodule classification method is realized.

Description

technical field [0001] The invention belongs to the field of image processing and medical integration, and specifically relates to a method for classifying benign and malignant pulmonary nodules based on CT images. We extract features based on deep convolutional neural networks and visual features describing the texture and shape of pulmonary nodules. Three classifiers are trained for these three different features, and the results of all classifiers are weighted and averaged to obtain the final classification result, which realizes the innovation of the lung nodule classification method based on CT images. Background technique [0002] Classification of pulmonary nodules based on CT images can generally be divided into three parts: pulmonary nodule segmentation, feature extraction, and classification of pulmonary nodules. Pulmonary nodule segmentation is based on the coordinates of the nodules marked by experts, and the nodules at the corresponding positions are segmented i...

AI Technical Summary

Problems solved by technology

In the present invention, when we perform feature layer fusion, a feature may be affected by other features, and then the spatial distribution of these features will change, and these changes will lead to poor classification performance

Images