HICT: High-precision 3D CBCT reconstruction from a single X-ray

TL;DR

This paper introduces HiCT, a novel two-stage framework that reconstructs high-fidelity 3D CBCT images from a single panoramic X-ray, addressing limitations of current methods in accuracy and geometric consistency.

Contribution

The paper presents HiCT, a new approach combining a diffusion model and a ray-based attention network, along with XCT dataset, to improve single X-ray 3D CBCT reconstruction accuracy.

Findings

HiCT outperforms existing methods in reconstruction accuracy.

The approach achieves geometrically consistent 3D reconstructions.

Extensive experiments validate clinical applicability.

Abstract

Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.