A low-dose CT image denoising method based on state space model
Year: 2024
Type: conference-paper
Abstract: Low-dose CT medical imaging techniques introduce noise while reducing radiation risks, necessitating denoising processing. However, existing mainstream denoising methods face a difficult trade-off between preserving image detail information and accurately removing noise. To address this issue, we propose a low-dose CT image denoising method based on a state space model. Firstly, a dynamic edge information enhancement module is introduced to automatically extract edge information from images using a learnable LoG operator and fuse it into feature layers at different scales to suppress edge information loss caused by denoising processes. Secondly, a U-net encoder based on state space estimation is designed to dynamically model spatial relationships between pixels through neighborhood filtering, enabling consideration of local differences in pixel values during denoising and better preservation of edges and textures. Compared to existing denoising methods, our approach achieves stable noise removal in low-dose CT images while preserving the original texture structure.
Authors: Kuankuan Peng, Shihua Gong
Institution: Huazhong University of Science and Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4403244492