CBCT image denoising based on multi-scale wavelet transform

Cone-Beam Computed Tomography (CBCT) has always been in the forefront of medical image processing. The denoising as a image pre-processing, has a great affected on the image analysis and recognition. In this paper, a new algorithm for image denoising was proposed. By thresholding the interscale wavelet coefficient magnitude sum(WCMS) within a cone of influence (COI), the wavelet coefficients are classified into 2 categories: irregular coefficients, and edge-related and regular coefficients. They are processed by different ways. Meanwhile according to the projection image sequences characteristics in CBCT system, an effective noise variance estimated methods was proposed. The experiment shows that our algorithm can improve PSNR form 1.3dB to 2.6dB, and the image border is more clearly.