Pulmonary nodule detection based on model fusion and adaptive false positive reduction

Lung cancer is the leading cause of cancer death worldwide, and most patients are diagnosed with advanced stages for lack of symptoms in the early stages of the disease, leading to poor prognosis. Thus, it is an urgent need to propose an accurate and fast pulmonary nodule detection network. In this paper, a model fusion based 2.5D pulmonary nodule detection network is proposed. In the first stage, the Weight Box Fusion (WBF) algorithm is introduced to make a fusion of the nodule candidates proposed by two mighty detection networks and yield a more accurate bounding box of nodule candidates. This is to determine the adaptive rate of the false positive reduction stage. The downside of model fusion is that it would generate many false positive candidates. So in the second stage, an adaptive 3D Convolutional Neural Network (CNN) architecture is designed to reduce the false positive candidates. The architecture can adjust the weights of soft assignment according to the diameter of nodules. By the experimental results on publicly available LUNA16, it demonstrates that 97.4% sensitivity can be obtained with an average of only 9.67 candidates per scan in our work that can compete with the state-of-the-art (SOTA) works. Besides, a 0.965 competition performance metric (CPM) is obtained on LUN16 and SOTA results from 1/8 to 1 FPs/Scan, which greatly outperforms other existing methods.