FD-DiT: Frequency Domain-Directed Diffusion Transformer for Low-Dose CT Reconstruction

TL;DR

FD-DiT introduces a frequency domain-guided diffusion transformer that enhances low-dose CT image reconstruction by effectively suppressing noise and artifacts while preserving fine details, outperforming existing methods.

Contribution

The paper proposes a novel frequency domain-directed diffusion transformer with a hybrid denoising network and dynamic fusion for improved LDCT reconstruction.

Findings

Superior noise and artifact suppression at the same dose levels

Enhanced preservation of fine anatomical details

Outperforms state-of-the-art reconstruction methods

Abstract

Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models has been a promising approach for image generation. Nevertheless, existing methods exhibit limitations in preserving finegrained image details. To address this issue, frequency domain-directed diffusion transformer (FD-DiT) is proposed for LDCT reconstruction. FD-DiT centers on a diffusion strategy that progressively introduces noise until the distribution statistically aligns with that of LDCT data, followed by denoising processing. Furthermore, we employ a frequency decoupling technique to concentrate noise primarily in high-frequency domain, thereby facilitating effective capture of essential anatomical structures and fine details. A hybrid denoising network is then utilized to optimize the overall data reconstruction process. To enhance the capability in recognizing high-frequency noise, we incorporate sliding sparse local attention to leverage the sparsity and locality of shallow-layer information, propagating them via skip connections for improving feature representation. Finally, we propose a learnable dynamic fusion strategy for optimal component integration. Experimental results demonstrate that at identical dose levels, LDCT images reconstructed by FD-DiT exhibit superior noise and artifact suppression compared to state-of-the-art methods.