The Gap in the Thickness: Estimating Effectiveness of Pulmonary Nodule Detection in Thick- and Thin-Section CT Images with 3D Deep Neural Networks

•A 3D convolutional neural network model has been developed to detect pulmonary nodule in either thick or thin section LDCT.•A set of CT scans have been annotated for pulmonary nodules in an efficient three-level protocol, correct and improve the annotation with trained neural networks proposal.•A performance gap between the thick and thin scans for pulmonary nodule detection by experienced pulmonary experts, regarding both false negative and false positive has been observed.•Neural network models, achieving competitive detection performance, can help reduce false negative and trade off the false negative for sensitivity.•A combination of the human and trained Neural network models is a promising way to achieve fast and accurate diagnose, even with thick scan setting, which is efficiency in screening, has cheap price, and has lower radiation dose