Low-dose CT image denoising method and system based on three-dimensional U-net

The invention belongs to the technical field of CT scanning, and particularly relates to a low-dose CT image denoising method and system based on three-dimensional U-net, and the method comprises the steps of taking to-be-processed low-dose CT projection data as the superposition of normal-dose CT projection and noise projection; carrying out denoising processing on low-dose CT projection data to be processed by utilizing the trained and optimized three-dimensional U-net network, wherein the denoising processing comprises firstly, extracting volume space characteristics of the input low-dose CT projection data by utilizing a three-dimensional U-net network encoder, simultaneously performing a plurality of downsampling operations on the input data to obtain volume feature mapping so as to capture underlying features of the multi-scale three-dimensional context information; and then, using a decoder for carrying out reconstruction and progressive up-sampling on the bottom layer features to predict a full-resolu