Streaking artifacts suppression for cone-beam computed tomography with the residual learning in neural network

This study aims to address and test a new residual learning algorithm in neural network applied to the projection data to generate high qualified imaging by reducing the streaking artifacts in cone-beam computed tomography (CBCT). Since the streaking artifacts have a large relationship with the noise on the projection, a residual objective upon Poisson noise corresponding to the image was proposed. As the prior, the convolution neural network (CNN) was constructed to residual learning based on the simulated label and exploited to eliminate the artifacts in the slice. To illustrate the robustness and applicability of CNN, the proposed method is evaluated using CBCT images. For the simulated projection, the PSNR and SSIM of the proposed method were dramatically increased by 15.4% and 85.9% of that with raw projection; for the true projection, the PSNR and SSIM were increased by 14.9% and 56.2%, respectively. Study results show effective results, and the proposed method is practical and attractive as a preferred solution to CT streaking artifacts suppression.