Noise reduction in CT images using a selective mean filter

C. Anam, K. Adi, H. Sutanto, Z. Arifin, W. S. Budi, T. Fujibuchi, G. Dougherty

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)


Background: Noise reduction is a method for reducing CT dose; however, it can reduce image quality. Objective: This study aims to propose a selective mean filter (SMF) and evaluate its effectiveness for noise suppression in CT images. Material and Methods: This experimental study proposed and implemented the new noise reduction algorithm. The proposed algorithm is based on a mean filter (MF), but the calculation of the mean pixel value using the neighboring pixels in a kernel selectively applied a threshold value based on the noise of the image. The SMF method was evaluated using images of phantoms. The dose reduction was estimated by comparing the image noise acquired with a lower dose after implementing the SMF method and the noise in the original image acquired with a higher dose. For comparison, the images were also filtered with an adaptive mean filter (AMF) and a bilateral filter (BF). Results: The spatial resolution of the image filtered with the SMF was similar to the original images and the images filtered with the BF. While using the AMF, spatial resolution was significantly corrupted. The noise reduction achieved using the SMF was up to 75%, while it was up to 50% using the BF. Conclusion: SMF significantly reduces the noise and preserves the spatial resolution of the image. The noise reduction was more pronounced with BF, and less pronounced with AMF.

Original languageEnglish
Pages (from-to)623-634
Number of pages12
JournalJournal of Biomedical Physics and Engineering
Issue number5
Publication statusPublished - 2020

All Science Journal Classification (ASJC) codes

  • Bioengineering
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Noise reduction in CT images using a selective mean filter'. Together they form a unique fingerprint.

Cite this