A low-dose CT image processing system based on noise artifact suppression convolutional neural network

Abstract

The invention discloses a low-dose CT image processing system based on a noise artifact suppression convolutional neural network. The system includes: an image preprocessing module, which is used to obtain multiple sets of matched low-dose CT images V<s><ld>and conventional dose CT images V<s><rd> and to subtract V<s><ld> and V<s><ld> to obtain noise artifact image Ns; a noise artifact suppression convolutional neural network building module, which is used for using V<s><ld> as a training image and Ns as a label image to establish a mapped convolutional neural network between V<s><ld> and Ns;a network training module, configured to train a noise artifact suppression convolutional neural network by reducing a loss function of the neural network; a network processing module, which is usedfor inputting a low-dose CT image to be processed V<t><ld> to the mapping convolutional neural network for processing and obtaining a predicted noise artifact image N<t>; and a noise artifact suppression module, which is used for subtracting N<t> from V<t><ld> to obtain a noise artifact suppressed image V<t>. The present invention can effectively suppress noise in low dose CT data Acoustic artifacts, the image quality after processing can meet the clinical analysis, diagnosis and other requirements, and the image effect of low-dose CT imaging is improved.

Description

technical field [0001] The invention relates to image processing technology, in particular to a low-dose CT image processing system based on noise artifact suppression convolutional neural 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 attenuation information of objects through ray projection measurement of objects. It is one of the conventional and effective clinical medical diagnostic tools at present. It has become an indispensable inspection and diagnosis method in the field of medical imaging to provide rich three-dimensional human organ tissue information for clinicians' diagnosis and prevention. However, with the popularity of CT tomography in clinical diagnosis, especially in routine examinations, the radiation dose in CT scanning has attracted more and more attention. A large number of clinical studies have shown that CT rad...

AI Technical Summary

Problems solved by technology

[0005] Although RED-CNN is superior to traditional methods in terms of subjective visual effect and objective evaluation indicators such as peak signal-to-noise ratio, structural similarity and root mean square error, it is the best for low-dose CT. The denoising effect of the image has reached the current advanced level, but the network complexity of RED-CNN is high, and the operation takes a long time

Images