Ordered-subsets Multi-diffusion Model for Sparse-view CT Reconstruction

2025-05-15

AI Summary

In sparse-view CT reconstruction, high redundancy in raw projection data, severe loss of fine anatomical details, and low learning efficiency of diffusion models pose significant challenges. To address these issues, this paper proposes the Ordered Subset Multi-Diffusion Model (OSMM). OSMM introduces a novel ordered subset partitioning strategy, synergistically integrating Multi-Branch Separate Diffusion Modeling (MSDM) for localized, high-fidelity reconstruction with One-Step Whole-sinogram Diffusion Modeling (OWDM) to enforce global consistency. The framework operates in an unsupervised training paradigm and enables cross-sparsity adaptive reconstruction without retraining. Extensive experiments demonstrate that OSMM substantially improves detail preservation and noise robustness across diverse sparse-view configurations. Quantitatively and qualitatively, it outperforms state-of-the-art diffusion-based methods in reconstruction accuracy, structural fidelity, and perceptual quality. Moreover, OSMM exhibits strong clinical generalizability and stability under varying acquisition conditions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Data transparency and provenance

Abstract

Score-based diffusion models have shown significant promise in the field of sparse-view CT reconstruction. However, the projection dataset is large and riddled with redundancy. Consequently, applying the diffusion model to unprocessed data results in lower learning effectiveness and higher learning difficulty, frequently leading to reconstructed images that lack fine details. To address these issues, we propose the ordered-subsets multi-diffusion model (OSMM) for sparse-view CT reconstruction. The OSMM innovatively divides the CT projection data into equal subsets and employs multi-subsets diffusion model (MSDM) to learn from each subset independently. This targeted learning approach reduces complexity and enhances the reconstruction of fine details. Furthermore, the integration of one-whole diffusion model (OWDM) with complete sinogram data acts as a global information constraint, which can reduce the possibility of generating erroneous or inconsistent sinogram information. Moreover, the OSMM's unsupervised learning framework provides strong robustness and generalizability, adapting seamlessly to varying sparsity levels of CT sinograms. This ensures consistent and reliable performance across different clinical scenarios. Experimental results demonstrate that OSMM outperforms traditional diffusion models in terms of image quality and noise resilience, offering a powerful and versatile solution for advanced CT imaging in sparse-view scenarios.

Problem

• Improves sparse-view CT reconstruction using ordered-subsets diffusion
• Reduces redundancy and enhances fine detail reconstruction
• Ensures robustness across varying CT sinogram sparsity levels

Innovation

• Divides CT data into subsets for targeted learning
• Integrates global constraint with complete sinogram data
• Uses unsupervised framework for robustness and generalizability