CT-denoimer: efficient contextual transformer network for low-dose CT denoising.
Authors
Affiliations (6)
Affiliations (6)
- School of Computer Science, Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA.
- College of Computer Science and Engineering, Qufu Normal University - Rizhao Campus, No. 80 Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA.
- School of Computer Science, Qufu Normal University, Yantai Road 80, Rizhao, Shandong, 276827, CHINA.
- Qufu Normal University, 80# Yantai Road, Donggang District, Rizhao, Shandong, 276826, CHINA.
- Department of Biomedical Engineering, Fourth Military Medical University, 169 Changlexi Rd, Xi'an, Shaanxi, 710032, CHINA.
- Laboratory of Image Science and Technology, Southeast University, Rennes, nanjing, 215123, CHINA.
Abstract
Low-dose computed tomography (LDCT) effectively reduces radiation exposure to patients, but introduces severe noise artifacts that affect diagnostic accuracy. Recently, Transformer-based network architectures have been widely applied to LDCT image denoising, generally achieving superior results compared to traditional convolutional methods. However, these methods are often hindered by high computational costs and struggles in capturing complex local contextual features, which negatively impact denoising performance. In this work, we propose CT-Denoimer, an efficient CT Denoising Transformer network that captures both global correlations and intricate, spatially varying local contextual details in CT images, enabling the generation of high-quality images. The core of our framework is a Transformer module that consists of two key components: the Multi-Dconv head Transposed Attention (MDTA) and the Mixed Contextual Feed-forward Network (MCFN). The MDTA block captures global correlations in the image with linear computational complexity, while the MCFN block manages multi-scale local contextual information, both static and dynamic, through a series of Enhanced Contextual Transformer (eCoT) modules. In addition, we incorporate Operation-Wise Attention Layers (OWALs) to enable collaborative refinement in the proposed CT-Denoimer, enhancing its ability to more effectively handle complex and varying noise patterns in LDCT images. Extensive experimental validation on both the AAPM-Mayo public dataset and a real-world clinical dataset demonstrated the state-of-the-art performance of the proposed CT-Denoimer. It achieved a peak signal-to-noise ratio (PSNR) of 33.681 dB, a structural similarity index measure (SSIM) of 0.921, an information fidelity criterion (IFC) of 2.857 and a visual information fidelity (VIF) of 0.349. Subjective assessment by radiologists gave an average score of 4.39, confirming its clinical applicability and clear advantages over existing methods. This study presents an innovative CT denoising Transformer network that sets a new benchmark in LDCT image denoising, excelling in both noise reduction and fine structure preservation.