Continuity-driven Synergistic Diffusion with Neural Priors for Ultra-Sparse-View CBCT Reconstruction

2026-02-08

AI Summary

This work addresses the challenge of ultra-sparse-view cone-beam computed tomography (CBCT) reconstruction, where severe undersampling artifacts and inter-slice inconsistencies—stemming from extremely limited angular sampling—compromise diagnostic reliability. To overcome these limitations, the authors propose a neural prior–driven continuous 3D attenuation representation, integrated with a dual-path collaborative diffusion mechanism that jointly leverages sinogram (Sino-RD) and digital radiograph (DR-RD) data. A dual-projection reconstruction fusion (DPRF) module is introduced to simultaneously optimize angular continuity and inter-slice consistency. This approach is the first to preserve both 3D structural integrity and view continuity under ultra-sparse sampling conditions, effectively suppressing artifacts while recovering fine textural details. Quantitative and qualitative evaluations demonstrate superior reconstruction quality compared to current state-of-the-art methods.

Technology Category

• Computer Vision: 3D Computer Vision
• Reasoning under Uncertainty: Uncertainty Representations
• Machine Learning: Multi-instance/Multi-view Learning

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
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

The clinical application of cone-beam computed tomography (CBCT) is constrained by the inherent trade-off between radiation exposure and image quality. Ultra-sparse angular sampling, employed to reduce dose, introduces severe undersampling artifacts and inter-slice inconsistencies, compromising diagnostic reliability. Existing reconstruction methods often struggle to balance angular continuity with spatial detail fidelity. To address these challenges, we propose a Continuity-driven Synergistic Diffusion with Neural priors (CSDN) for ultra-sparse-view CBCT reconstruction. Neural priors are introduced as a structural foundation to encode a continuous threedimensional attenuation representation, enabling the synthesis of physically consistent dense projections from ultra-sparse measurements. Building upon this neural-prior-based initialization, a synergistic diffusion strategy is developed, consisting of two collaborative refinement paths: a Sinogram Refinement Diffusion (Sino-RD) process that restores angular continuity and a Digital Radiography Refinement Diffusion (DR-RD) process that enforces inter-slice consistency from the projection image perspective. The outputs of the two diffusion paths are adaptively fused by the Dual-Projection Reconstruction Fusion (DPRF) module to achieve coherent volumetric reconstruction. Extensive experiments demonstrate that the proposed CSDN effectively suppresses artifacts and recovers fine textures under ultra-sparse-view conditions, outperforming existing state-of-the-art techniques.

Problem

• ultra-sparse-view CBCT reconstruction
• undersampling artifacts
• inter-slice inconsistency
• radiation dose reduction
• image quality

Innovation

• Neural Priors
• Synergistic Diffusion
• Ultra-Sparse-View CBCT
• Angular Continuity
• Inter-slice Consistency