FCDM: A Physics-Guided Bidirectional Frequency Aware Convolution and Diffusion-Based Model for Sinogram Inpainting

2024-08-26

AI Summary

To address severe sinogram incompleteness in sparse-view CT—causing reconstruction artifacts and physical inconsistency—this paper proposes a physics-guided, frequency-aware sinogram inpainting framework. Methodologically, it introduces bidirectional frequency-domain convolution for feature disentanglement; incorporates total absorption conservation and frequency-domain consistency as physics-based loss constraints; and integrates diffusion modeling with physical priors via Fourier-enhanced mask embedding and soft row-wise attenuation noise scheduling. Evaluated on both synthetic and real sparse-view CT data, the method achieves SSIM > 0.95 and PSNR > 30 dB, outperforming state-of-the-art methods by up to 33% in SSIM and 29% in PSNR. It significantly improves reconstruction fidelity, structural consistency, and physical interpretability while ensuring adherence to fundamental CT imaging principles.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Computed tomography (CT) is widely used in industrial and medical imaging, but sparse-view scanning reduces radiation exposure at the cost of incomplete sinograms and challenging reconstruction. Existing RGB-based inpainting models struggle with severe feature entanglement, while sinogram-specific methods often lack explicit physics constraints. We propose FCDM, a physics-guided, frequency-aware sinogram inpainting framework. It integrates bidirectional frequency-domain convolutions to disentangle overlapping features while enforcing total absorption and frequency-domain consistency via a physics-informed loss. To enhance diffusion-based restoration, we introduce a Fourier-enhanced mask embedding to encode angular dependencies and a frequency-adaptive noise scheduling strategy that incorporates a soft row-wise absorption constraint to maintain physical realism. Experiments on synthetic and real-world datasets show that FCDM outperforms existing methods, achieving SSIM over 0.95 and PSNR above 30 dB, with up to 33% and 29% improvements over baselines.

Problem

• Addresses incomplete sinograms in sparse-view CT imaging
• Overcomes feature entanglement in RGB-based inpainting models
• Enhances physical realism in sinogram reconstruction

Innovation

• Physics-guided bidirectional frequency-aware convolutions
• Fourier-enhanced mask embedding for angular dependencies
• Frequency-adaptive noise scheduling with absorption constraints