Cover Image

WaveletDFDS-net: a dual forward denoising stream network for low-dose CT noise reduction

The challenge of denoising low-dose computed tomography (CT) has garnered significant research interest due to the detrimental impact of noise on CT image quality, impeding diagnostic accuracy and image-guided therapies. This paper introduces an innovative approach termed the Wavelet Domain Dual For...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhou, Yusheng (Author) , Kong, Zhengmin (Author) , Huang, Tao (Author) , Ahn, Euijoon (Author) , Li, Hao (Author) , Ding, Li (Author)
Format: Article (Journal)
Language:English
Published: 2024
In: Electronics
Year: 2024, Volume: 13, Issue: 10, Pages: 1-16
ISSN:2079-9292
DOI:10.3390/electronics13101906
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.3390/electronics13101906
Verlag, kostenfrei, Volltext: https://www.mdpi.com/2079-9292/13/10/1906
Get full text
Author Notes:Yusheng Zhou, Zhengmin Kong, Tao Huang, Euijoon Ahn, Hao Li and Li Ding
Description
Summary:The challenge of denoising low-dose computed tomography (CT) has garnered significant research interest due to the detrimental impact of noise on CT image quality, impeding diagnostic accuracy and image-guided therapies. This paper introduces an innovative approach termed the Wavelet Domain Dual Forward Denoising Stream Network (WaveletDFDS-Net) to address this challenge. This method ingeniously combines convolutional neural networks and Transformers to leverage their complementary capabilities in feature extraction. Additionally, it employs a wavelet transform for efficient image downsampling, thereby preserving critical information while reducing computational requirements. Moreover, we have formulated a distinctive dual-domain compound loss function that significantly enhances the restoration of intricate details. The performance of WaveletDFDS-Net is assessed by comparative experiments conducted on public CT datasets, and results demonstrate its enhanced denoising effect with an SSIM of 0.9269, PSNR of 38.1343 and RMSE of 0.0130, superior to existing methods.
Item Description:Gesehen am 06.06.2025
Physical Description:Online Resource
ISSN:2079-9292
DOI:10.3390/electronics13101906

Similar Items