Low-dose CT imaging method, device and system based on deep dense network

Abstract

The invention provides a low-dose CT imaging method, device and system based on a deep dense network. A deep dense network DenseNet is innovatively applied to two processing methods of projection space pre-processing and image space post-processing, and the convolutional residual neural network is utilized to fully understand the information of CT image data and CT projection data. According to the method, the difference between star-strip-shaped artifacts and human tissues and organs is effectively distinguished through full utilization of the image features by the DenseNet, and the star-strip-shaped artifacts, noise and tissue and organ feature structure components are effectively separated, so that the image quality is greatly improved. Compared with other networks with the same scale,the DenseNet has the advantages that the parameter quantity is reduced to a certain extent, so that the requirement of the storage space is greatly reduced. The operation speed is remarkably improved,and the processing effect is superior to that of other traditional image denoising algorithms and deep learning methods.

Description

technical field [0001] The invention belongs to the technical field of computer tomography and relates to CT imaging technology, in particular to a low-dose CT imaging method, device and system based on a deep dense network. Background technique [0002] X-ray computer tomography (X-ray Computer Tomography, CT) technology is an imaging technology that obtains accurate and non-destructive cross-sectional ray attenuation information through X-ray projection measurement of the human body. It is currently the most widely used routine and effective clinical medical diagnosis. One of the tools, it can provide detailed and rich human organ tissue information for clinicians' detection and diagnosis, and has become an indispensable inspection and diagnosis method in the field of medical imaging. However, with the popularity of CT tomography in clinical diagnosis, especially in routine examination, the radiation dose in CT scanning has gradually attracted people's attention. A large ...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above problems, the present invention provides a low-dose CT imaging method, device and system based on a deep dense network, which can improve the effect of the current post-processing algorithm and improve the ability to process low-dose CT images with too low dose and too high noise , and overcome the problem that existing low-dose CT image processing methods cannot better distinguish star-streaked artifacts and organ tissue details

Images