Deep Learning-driven Pulmonary Nodule Detection from CT Images: Challenges, Current Status and Future Directions

Automatic detection of pulmonary nodule based on CT images can significantly improve the diagnosis and treatment of lung cancer. Based on the characteristics of CT image and pulmonary nodule, this study summarizes the challenges and recent progresses of CT image-based pulmonary nodule detection using various deep learning models. The study focuses on the review of major research developments by investigating their technical details, strengths and shortcomings. In light of the current application status of pulmonary nodule detection, a research agenda that aims to better apply and improve deep learningdriven pulmonary nodule detection technologies was given in this study.