Double-attention generative adversarial network for noise reduction and artifact removal of low-dose CT image

Abstract

The invention belongs to the technical field of CT imaging, and discloses a deep learning method for suppressing noise and artifacts in a low-dose CT image and facilitating later accurate medical diagnosis and analysis. The specific technical scheme is as follows: the double-attention generative adversarial network for noise reduction and artifact removal of the low-dose CT image is used for extracting non-uniform and irregular noise features and tissue texture features with complex distribution respectively; a Res2Net discriminator network for multi-scale feature extraction is designed, so that the discrimination capability of the discriminator is improved, and the stability and robustness of adversarial training are enhanced; a multi-description loss function combining artifact attentionloss, artifact consistency loss, structure constraint loss, adversarial loss and pixel-level L1 loss is designed to further improve the function of each sub-network. According to the method, the phenomenon of under-noise reduction or over-noise reduction caused by high similarity of noise artifacts and tissue structure distribution is avoided.

Description

technical field [0001] The invention belongs to the technical field of CT imaging, and discloses a deep learning method for suppressing noise and artifacts in low-dose CT images and facilitating accurate medical diagnosis and analysis in the later stage. Background technique [0002] Computed tomography (CT) is a non-destructive testing technology widely used in biomedicine, image-guided intervention, security inspection, industrial and agricultural production, geology and petroleum exploration. As an important auxiliary means of medical diagnosis and treatment, CT imaging is fast and accurate, and can fully present the three-dimensional information of the inspected part, and it can play a role in the detection of bone injuries, tumors and nodes, vascular lesions, pulmonary hydrops, and cancerous cells. play an irreplaceable role. At present, CT examination is closely related to everyone. Routine physical examination, specific medical diagnosis and treatment, etc. need to b...

AI Technical Summary

Problems solved by technology

However, the biggest disadvantage of this method is that the obtained LDCT image density resolution is low, and there are obvious speckle noise and stripe artifacts; reducing the tube voltage is also an option to reduce X-ray radiation, but the X-ray penetration is reduced while the tube voltage is reduced. The penetration ability will also decrease accordingly, which will lead to serious degradation of imaging quality; ②Reducing the number of X-rays is also the main way to reduce the radiation dose. The projection data obtained by such methods (such as internal scanning, less viewing angle, and limited angle) are incomplete. Reconstruction algorithm performance has higher requirements

Images