Lung Cancer Detection using a Dilated CNN with VGG16
Yu Lu, Huanwen Liang, Shijie Shi, Xianghua Fu
Abstract
Lung nodules are an early manifestation of lung cancer. Early detection of lung nodules plays a vital role in improving the survival rate of patients. Computed tomography (CT) has fast scanning speed, high image size, and can capture tiny areas. The application of CT for clinical diagnosis is an effective method. We use convolutional neural network (CNN) to study the algorithm of lung nodule detection and diagnosis based on CT images. This paper is based on a lung nodule segmentation network combining VGG-16 and dilated convolution. And compared with traditional lung nodule segmentation methods and Inception v2, XOR evaluation coefficient, Hausdorff distance, Jaccard similarity coefficient, accuracy, sensitivity and specificity were used as segmentation evaluation indexes. VGG-16 is superior to traditional image processing methods in all indicators. The accuracy of VGG-16 is as high as 0.971, the false detection rate is only 0.101, and the missed detection rate is only 0.074. The segmented image result is closest to Ground Truth, and there is no problem of incorrect segmentation of lung parenchyma and lung nodules. The VGG-16 proposed in this paper improves the accuracy of segmenting lung nodules, and is superior to traditional image processing methods in various performance indicators, which can effectively help experts diagnose lung nodules.