Abstract: The continuous development and extensive use of CT in modern medical practice has raised a public concern over the associated radiation dose to the patient. Hence, extensive efforts have been made to design better image reconstruction or image processing methods for low-dose CT over the past years. The recent explosive development of learning type algorithm suggests new thinking and huge potential for the CT imaging field under the imaging big data environment. This paper summarizes the development and implementation of low dose CT scans from the following aspects: sparse learning and deep learning. The research status of low dose CT technology and feature learning models are also summarized. Finally, both the current research focus and the future research prospect are discussed and analyzed.