FSP-Diff: Full-Spectrum Prior-Enhanced DualDomain Latent Diffusion for Ultra-Low-Dose Spectral CT Reconstruction

2026-02-08

AI Summary

This work addresses the severe artifacts and detail loss in ultra-low-dose photon-counting spectral CT imaging, where energy-specific projection data suffer from extremely low signal-to-noise ratios. To overcome this challenge, the authors propose a full-spectrum prior–enhanced dual-domain latent diffusion framework that synergistically combines projection-domain denoising with image-domain direct reconstruction. By leveraging a high-SNR full-spectrum prior to guide collaborative reconstruction across multiple energy channels and performing diffusion synthesis efficiently in a compact latent space, the method uniquely integrates dual-domain feature fusion, full-spectrum prior incorporation, and multi-path latent embedding. This approach simultaneously suppresses noise, preserves fine textural details, and substantially reduces computational complexity. Extensive experiments on both simulated and real data demonstrate its superiority over existing methods, achieving breakthroughs in image quality and reconstruction efficiency, thereby showing strong potential for clinical translation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Feature Construction/Reformulation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Spectral computed tomography (CT) with photon-counting detectors holds immense potential for material discrimination and tissue characterization. However, under ultra-low-dose conditions, the sharply degraded signal-to-noise ratio (SNR) in energy-specific projections poses a significant challenge, leading to severe artifacts and loss of structural details in reconstructed images. To address this, we propose FSP-Diff, a full-spectrum prior-enhanced dual-domain latent diffusion framework for ultra-low-dose spectral CT reconstruction. Our framework integrates three core strategies: 1) Complementary Feature Construction: We integrate direct image reconstructions with projection-domain denoised results. While the former preserves latent textural nuances amidst heavy noise, the latter provides a stable structural scaffold to balance detail fidelity and noise suppression. 2) Full-Spectrum Prior Integration: By fusing multi-energy projections into a high-SNR full-spectrum image, we establish a unified structural reference that guides the reconstruction across all energy bins. 3) Efficient Latent Diffusion Synthesis: To alleviate the high computational burden of high-dimensional spectral data, multi-path features are embedded into a compact latent space. This allows the diffusion process to facilitate interactive feature fusion in a lower-dimensional manifold, achieving accelerated reconstruction while maintaining fine-grained detail restoration. Extensive experiments on simulated and real-world datasets demonstrate that FSP-Diff significantly outperforms state-of-the-art methods in both image quality and computational efficiency, underscoring its potential for clinically viable ultra-low-dose spectral CT imaging.

Problem

• ultra-low-dose
• spectral CT
• signal-to-noise ratio
• image artifacts
• structural detail loss

Innovation

• spectral CT
• latent diffusion
• full-spectrum prior
• ultra-low-dose
• dual-domain reconstruction