Pulmonary nodule detection is a very challenging task based on high-dimensional lung Computed Tomography (CT) images. Among many pulmonary nodule detection algorithms, the deep Convolutional Neural Network (CNN) is the most attractive one. In this kind of networks, the Two-Dimensional (2D) CNNs with many pre-trained models and high detection efficiency are widely used. However, the nature of pulmonary nodules is the Three-Dimensional (3D) lesion, so that the 2D CNNs will inevitably cause information loss and thereby affect the detection accuracy. The 3D CNNs can make full use of the spatial information of CT images and effectively improve the detection accuracy, but the 3D CNNs have shortcomings such as many parameters, large calculation consumption and high risk of over fitting. In order to take the advantages of the two networks, a pulmonary nodule detection model based on a deep mixed CNN was proposed. By deploying 3D CNN in the shallow layer of the neural network model and 2D CNN in the deep layer of the model, and adding a deconvolution module to fuse multi-layer image features together, the model parameters were reduced and the generalization ability and the detection efficiency of the model were improved without decreasing the detection accuracy. Experimental results on LUNA16 dataset show that the proposed model has the sensitivity reached 0.924 under the condition of average 8 false positives per scan, which outperforms the existing state-of-the-art models.

According to the feature of high-dimensional data, the number of variables is usually larger than the sample size and the data are often heterogeneous, a robust and effective feature selection method was proposed by using the dimensional reduction technique of variable selection and the modal regression based estimation method. The estimation algorithm was given by using Local Quadratic Algorithm (LQA) and Expectation-Maximum (EM) algorithm, and the selection method of the parameter adjustment was also discussed. Data analysis of the simulation shows that the proposed method is overall better than the least square and median regression based regularized method. Compared with the existing methods, the proposed method has higher prediction ability and stronger robustness especially for the non-normal error distribution.