eess.IVNov 12, 2026

RouteDiff: Low-Dose CT Denoising via Fidelity-Refinement Routing and Hypergraph State Regulation

Authors: Xinyuan Wang, Ruili Li, Tianyang Li, Yan Li, Xuepeng Liu

Organizations: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China · University of Dundee, Dundee DD1 4HN, United Kingdom · Tohoku University School of Medicine, Sendai 980-8575, Japan

Abstract

Diffusion models have become a strong prior for low-dose computed tomography (LDCT) restoration. However, existing samplers apply one structure-detail trade-off to the whole image, set the restoration emphasis of each step by the timestep, and derive each next state recursively from the current one, carrying its errors forward. We propose RouteDiff, a state-aware dual-route diffusion framework that routes detail to where it can be trusted, regulates each reverse step by the state it has reached, and re-enters the trajectory from an anchored estimate. Fidelity-Refinement Routing (FRR) equips one shared U-Net with a conservative fidelity route and a detail-oriented refinement route, fuses them pixel-wise with a confidence map, and exposes their disagreement as route evidence. Hypergraph State Regulation (HSR) organizes the current features and this evidence into a state hypergraph, whose soft hyperedges group scattered regions in the same state. Its readout yields an ordered stage judgment that modulates the bottleneck, and its incidence guides feature interaction in the skip connections. Estimate-Anchored Re-entry (EAR) re-projects a route-aware anchor onto the trajectory at a fixed step and hands the new state back to HSR to be judged again. With the ten network evaluations of its baseline, RouteDiff achieves the best peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) on four datasets with inserted, real and simulated noise (40.95 dB and 95.13% on Mayo 2020; 45.18 dB and 97.23% on Mayo 2016). It also generalizes to unseen doses of real scans and yields the highest Dice (80.92%) in downstream segmentation.

Figures & tables

Explore similar work

CardsList
  1. FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising

    Aug 24, 2025Zhihao Chen, Qi Gao, Zilong Li +4Diffusion Models for Image RestorationMedical Imaging Foundation Models

  2. GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization

    Jul 11, 2026Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor +3Domain GeneralizationImage Reconstruction

  3. ProSAC-CT: Progressive Spectral-Anatomical Co-Guided Multi-Stage Diffusion Model for Low-Dose CT Denoising

    Jul 2, 2026Xuepeng Liu, Zetong Liu, Renyiming Li +5Diffusion Models for Image RestorationDiffusion Model Guidance