%0 Journal Article
%T Variable Step Normalized Least Mean Square Guided by Composite Desired Signal for Few-View Computed Tomography Denoising
%A Yuxuan Zhou
%A Dongjiang Ji
%A Qi Zhang
%J Journal of Signal and Information Processing
%P 1-17
%@ 2159-4481
%D 2025
%I Scientific Research Publishing
%R 10.4236/jsip.2025.161001
%X <b>Background:</b> Low-dose CT provides essential diagnostic information while minimizing radiation exposure through few-view reconstruction techniques. However, these techniques often introduce noise and artifacts, affecting diagnostic accuracy. Although <math xmlns='http://www.w3.org/1998/Math/MathML'>
 <mrow>
  <msub>
   <mi>L</mi>
   <mn>0</mn>
  </msub>
  </mrow>
</math>

-smoothing regularization methods partially address these issues, their fixed sparsity constraint cannot adapt to CT image complex characteristics, and they remain highly sensitive to regularization parameter selection. <b>Objective:</b> To propose a novel CT image denoising method named Variable Step Normalized Least Mean Square <math xmlns='http://www.w3.org/1998/Math/MathML'>
 <mrow>
  <msub>
   <mi>L</mi>
   <mn>0</mn>
  </msub>
  </mrow>
</math>

-smoothing (VSNLMS-<math xmlns='http://www.w3.org/1998/Math/MathML'>
 <mrow>
  <msub>
   <mi>L</mi>
   <mn>0</mn>
  </msub>
  </mrow>
</math>

) that achieves an optimal balance between noise reduction and structural preservation while reducing sensitivity to regularization parameter selection. <b>Methods:</b> The VSNLMS-<math xmlns='http://www.w3.org/1998/Math/MathML'>
 <mrow>
  <msub>
   <mi>L</mi>
   <mn>0</mn>
  </msub>
  </mrow>
</math>

 method employs an adaptive framework that dynamically responds to local image characteristics. The variable step-size strategy enables precise calibration of processing intensity across regions with varying noise levels and detail complexity, ingeniously combining filtered back projection (FBP) reconstruction results with <math xmlns='http://www.w3.org/1998/Math/MathML'>
 <mrow>
  <msub>
   <mi>L</mi>
   <mn>0</mn>
  </msub>
  </mrow>
</math>

-smoothing to create a composite desired signal. <b>Conclusions:</b> This approach offers an effective solution for enhancing low-dose CT image quality and improving diagnostic reliability.
%K CT Image Denoising
%K Regularization Parameter
%K -Smoothing
%K VSNLMS
%K Few-View Reconstruction
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=143060