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

2026-07-02

AI Summary

This work addresses the challenges posed by low-dose CT (LDCT), where reduced radiation leads to severe quantum noise, streak artifacts, and texture degradation that obscure anatomical boundaries and compromise low-contrast structures. To tackle these issues, the authors propose a multi-stage diffusion model that jointly incorporates spectral and anatomical priors for the first time. The approach employs a three-stage collaborative optimization during reverse diffusion: an Anatomy-Prior-Guided Conditioning (APGC) module, a Residual Frequency Domain Decoupling Stage (RFDDS), and a Time-step Decoupled Denoising Decoder (TD3), enabling fine-grained restoration of boundary-sensitive structures. Evaluated on four LDCT benchmarks, the method significantly improves image fidelity, structural similarity, and perceptual quality, while effectively preserving diagnostically critical anatomical information, as demonstrated by enhanced performance in downstream classification tasks on the Mayo-2020 dataset.

Abstract

Low-dose computed tomography (LDCT) reduces radiation exposure but introduces stronger quantum noise, streak artifacts, and local texture degradation, which can obscure anatomical boundaries and weaken low-contrast structures. Diffusion models are promising for LDCT denoising by progressively recovering normal-dose CT (NDCT) images from degraded LDCT inputs, but existing methods often suffer from insufficient anatomical guidance, uncertain frequency-dependent recovery, and uniform reverse-process modeling. We propose ProSAC-CT, a progressive spectral-anatomical co-guided multi-stage diffusion model for image-domain LDCT denoising. ProSAC-CT integrates an anatomical-prior-guided conditioning (APGC) module, a residual frequency-domain decoupling stage (RFDDS), and a time-step-decoupling denoising decoder (TD3). APGC extracts LDCT-derived structural guidance, RFDDS enhances frequency-aware representations, and TD3 assigns them to different reverse-diffusion stages for anatomical stabilization, boundary refinement, and fine-detail recovery. Experiments on four LDCT degradation benchmarks show that ProSAC-CT improves image fidelity, structural similarity, perceptual quality, and information preservation over representative methods while better preserving boundary-sensitive anatomical details. Downstream anatomical-region classification on Mayo-2020 further indicates that ProSAC-CT retains task-relevant anatomical information, supporting its practical use for low-dose CT denoising.

Problem

• Low-dose CT
• Quantum noise
• Streak artifacts
• Anatomical boundaries
• Texture degradation

Innovation

• diffusion model
• anatomical guidance
• frequency-aware denoising
• multi-stage denoising
• low-dose CT