A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques

Abstract

Lung cancer is the top cause for deaths by cancers whose 5-year survival rate is less than 20%. To improve the survival rate of patients with lung cancers, the early detection and early diagnosis is significant. Furthermore, early detection of pulmonary nodules is essential for the detection and diagnosis of lung cancer in early stage. The National Lung Screening Trial (NLST) showed annual screening by low-dose computed tomography (LDCT) could help to reduce the deaths caused by lung cancer of high-risk subjects by 20% comparing with screening by chest radiography. In past decade, there has been lots of works on computer-aided detection (CADe) and computer-aided diagnosis (CADx) for pulmonary nodules in computed tomography (CT) scans, whose target is to detect, segment the nodules and further classify them into benign and malignant efficiently and precisely. This survey reviews some recent works on detection, segmentation and classification for pulmonary nodule in CT scans with deep learning techniques.