A Lung Cancer Detection and Recognition Method Combining Convolutional Neural Network and Morphological Features

Abstract

Lung cancer is the malignant tumor with the highest morbidity and mortality, and it is a great threat to human health. With the increasing refinement of lung cancer images, it provides a lot of useful information for the analysis and identification of lung cancer, and an important help to assist doctors in making accurate diagnosis. A considerable part of lung cancer manifests as nodules in the early stage. Pulmonary nodules are round or irregular lesions in the lungs, about 34% are lung cancers, and the rest are benign lesions. Therefore, the detection of pulmonary nodules is very important for the detection of early lung cancer. In this paper, some Computed Tomography (CT) images of the Lung Image Database Consortium (LIDC) dataset are adopted as training and testing data, data preprocessing is completed by intercepting pixels, normalization and other methods, data enhancement is realized such as rotation and scaling methods, and the pulmonary nodule sample library is expanded. Utilizing the constructed lung nodule sample library, train the Convolutional Neural Network (CNN) model, complete the detection and segmentation of pulmonary nodules, and exact the regions of pulmonary nodules. The size and regularity features of pulmonary nodules are extracted, and lung cancer recognition is realized according to the size and shape of pulmonary nodules. The experiment results show the lung cancer detection and identification method based on convolutional neural network with morphological features has higher accuracy.