Dense neural network lung tumor image recognition method fusing multi-scale features

Abstract

The invention discloses a dense neural network lung tumor image recognition method fusing multi-scale features, and the method comprises the steps: collecting and preprocessing CT modal medical images, extracting lesion ROI regions of different scales, and forming a multi-scale data set; wherein the focus ROI regions of different scales are provided with clinically marked benign or malignant tumortags; training the multi-scale data set in a dense neural network, constructing a dense neural network model, extracting a full connection layer feature vector and carrying out feature serial fusion;and obtaining a lung tumor classification result in the NSCR classifier. A dense neural network model constructed by the method is superior to an AlexNet model, bottom-layer new features can be minedagain by effectively utilizing high-layer information, transmission of the features among networks is enhanced, and feature reuse is realized and enhanced; the invention is deep in network depth, strong in network generalization capability and high in lung tumor classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of neural network image recognition, and in particular relates to a dense neural network image recognition method for lung tumors that integrates multi-scale features. Background technique [0002] Lung cancer is one of the malignant tumors with high morbidity and mortality among cancers. The incidence of lung cancer is increasing year by year, which seriously threatens human health. According to the 2019 American Cancer Statistics Report, lung cancer is one of the most common cancers. , accounting for 11.6% of all cancer cases, lung cancer is also the leading cause of cancer death, accounting for 18.4% of the total number of cancer deaths. According to the report of the National Cancer Center in 2019, the morbidity and mortality of lung cancer occupy the first place among all cancers. Medical imaging methods are widely used in the diagnosis of lung tumors, including ultrasound, X-ray imaging, and computeriz...

AI Technical Summary

Problems solved by technology

[0005] However, the accuracy of the above methods for lung tumor image recognition needs to be improved, and it is not very good for the classification of benign and malignant lung tumors.

Images