CE-DDIM: Conditional Efficient Diffusion Method for Cone-Beam CT Enhancement

Computed tomography (CT) provides high-quality imaging but is costly and exposes patients to relatively high radiation. Cone-beam CT (CBCT) offers faster, lower-dose, and more cost-effective 3D imaging but suffers from scatter, truncation, and noise that limit its clinical utility. In CBCT-to-CT image enhancement, diffusion models achieve strong performance but incur high computational cost. To tackle this problem, we propose Conditional Efficient DDIM (CE-DDIM), an efficient CBCT-to-CT image enhancement framework. CE-DDIM integrates a dual-head conditional U-Net trained with a heteroscedastic negative log-likelihood and total variation regularizer to jointly predict denoising targets and pixel-wise variance. Moreover, a multi-window Hounsfield Unit input is used to improve the reconstruction quality. This design enables high-fidelity reconstructions with 10 × reduction in steps compared to previous methods. On the SynthRAD2023 datasets, CE-DDIM improves both reconstruction fidelity and sampling efficiency over baselines, providing a practical solution for synthetic CT generation.