Advances in CT-based artificial intelligence techniques for lung nodule diagnosis

Lung cancer is one of the common malignancies worldwide. Lung nodules, defined as early stage manifestations, are critical for early detection and diagnosis to reduce mortality. In recent years, CT based artificial intelligence (AI) technology has made significant progress in medical image analysis. This review summarizes the applications of deep learning and radiomics in the segmentation and detection of lung nodules, differentiation between benign and malignant nodules, and prediction of lung cancer prognosis. It also presents the latest technical frontiers with the aim of providing new perspectives and methods for clinical practice.