Edge Protection and Global Attention Mechanism Densely Connected Convolutional Network for LDCT Denoising.

Low-dose computed tomography (LDCT) imaging can significantly reduce the radiation dose to a patient. However, a low radiation dose will cause considerable noise and artifacts in the image, seriously impacting the clinical diagnosis. To better solve the problems, we propose an edge protection and global attention mechanism densely connected convolutional network (EP–GAMNet) for LDCT denoising. First, edge information was extracted using the improved eight-directional Prewitt operator and then, passed to each convolutional block through skip connections. Subsequently, a multiscale feature extractor and global attention mechanism were used for feature extraction. The final predicted images were then obtained by the noise reduction module. Further, a compound loss function based on mean squared error and perceptual loss was used to enhance the texture detail and improve the visual quality of the image. Extensive experiments on Mayo and piglet datasets showed the effectiveness of the proposed method in reducing noise/artifacts while preserving edges. The peak-signal-to-noise ratio value of CT images of the AAPM dataset processed by the new model is 33.5712, and the structural similarity (SSIM) value is 0.9244. Moreover, it performed better than some classical methods in terms of objective indicators and subjective effects. The proposed model is robust and can effectively retain edge information and extract effective features from LDCT images. Moreover, it is effective in improving LDCT image quality. [ABSTRACT FROM AUTHOR]