RDDM: A Residual-Driven Drifting Model for High-Fidelity Low-Dose CT Denoising

TL;DR

The paper introduces RDDM, a novel residual-driven drifting model that achieves high-fidelity, real-time low-dose CT denoising by incorporating multi-step distribution evolution into a one-step process, outperforming existing methods.

Contribution

Proposes RDDM, a residual-driven drifting model that enables efficient, high-fidelity, one-step denoising for low-dose CT, with variants tailored for different application needs.

Findings

RDDM achieves state-of-the-art denoising performance among supervised methods.

RDDM-Fine produces reconstructions highly consistent with normal-dose CT, with superior PSNR, SSIM, and FID.

RDDM enables on-the-fly inference, denoising a 512x512 slice in about 15 ms.

Abstract

Low-dose CT (LDCT) denoising remains an important yet challenging problem in medical imaging. Although recent learning-based methods have shown promising performance, those optimized using classical pixel-level objectives often produce over-smoothed reconstructions. Existing mainstream generative models, such as diffusion models, have improved fidelity at the cost of expensive multi-step iterative inference, which limits their practicality for real-time use. To address this gap, we propose a Residual-Driven Drifting Model (RDDM) for effective, efficient, and high-fidelity LDCT denoising. Inspired by the recently proposed Drifting Models, RDDM incorporates the multi-step distribution evolution into the training dynamics through a residual drifting field, thereby enabling one-step denoising. Specifically, the residual drifting field is formed by an attractive force induced by the residuals between LDCT and normal-dose CT (NDCT) and a repulsive force induced by the generated residuals. In addition, by adjusting the parameter settings and incorporating pixel-level supervision, we develop three RDDM variants, covering application needs from detail preservation to stronger noise suppression. Extensive experiments demonstrate that RDDM achieves state-of-the-art denoising performance among supervised baselines. In particular, RDDM-Fine produces reconstructions that are highly consistent with NDCT, achieving superior PSNR and SSIM together with the best FID of 5.87 while preserving realistic anatomical textures. Moreover, RDDM enables on-the-fly inference, requiring only about 15 ms to denoise a single 512 x 512 LDCT slice. These results establish RDDM as a promising solution for high-fidelity and real-time LDCT denoising in clinical applications.