Low-dose CT image restoration and denoising method

Abstract

The invention discloses a low-dose CT image restoration and denoising method. The method comprises the following steps: simulating and generating a low-dose CT image required by training; performing fan-shaped beam projection transformation on the high-dose CT image to obtain projection data of a projection domain, performing exponential operation on an obtained projection matrix, adding Poisson noise, taking a logarithm, and converting the simulated projection data back to the image domain through a built-in back projection function of MATLAB to obtain a simulated low-dose CT image. Accordingto the low-dose CT image restoration and denoising method disclosed by the invention, the conversion from the low-dose CT image to the high-dose CT image is efficiently realized; detail parts on theCT image are effectively recovered, meanwhile, the complexity of the network can be reduced, the network training is accelerated, the reconstruction efficiency is improved, and the harm of the CT technology to a patient can be effectively reduced under the condition that the diagnosis of a doctor is not influenced.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to a low-dose CT image restoration and denoising method. Background technique [0002] In recent years, with the continuous development of medical imaging technology and the increasing prominence of its practical application advantages in the medical field, many new medical imaging technologies, such as CT imaging technology, can provide important basis for clinical diagnosis through their reasonable application , has become an indispensable auxiliary diagnostic tool in today's medical field. CT images are mainly generated by CT imaging technology for medical diagnosis and are tools for assisting doctors in diagnosis. The basic principle of CT imaging technology is to use X-ray beams to scan a layer of a certain thickness of the human body inspection site. The X-rays that pass through this layer are received by the detector and converted into visible light...

AI Technical Summary

Problems solved by technology

When the tube current decreases, the number of photons received by the detector also decreases, resulting in a "photon starvation" effect, causing the projection data to be polluted by noise, and the CT image reconstructed from the projection data not only has obvious noise, but also produces Streak artifacts, which adversely affect clinical diagnosis

In response to these problems, many algorithms for improving the quality of low-dose CT images have been proposed, which can be divided into projection domain denoising algorithms, image reconstruction algorithms, and image domain denoising algorithms, etc., but these algorithms still have deficiencies. Need to use the original projection data, which is difficult to obtain in practice, and the algorithm complexity is high and time-consuming

At the same time, although most of the existing methods can denoise and remove artifacts on low-dose CT images, it is difficult to restore some details on CT images.

Images