Human-Guided Shade Artifact Suppression in CBCT-to-MDCT Translation via Schr\"odinger Bridge with Conditional Diffusion

TL;DR

This paper introduces a novel CBCT-to-MDCT translation framework using Schrödinger Bridge and human-guided diffusion, improving artifact suppression and anatomical fidelity with real-time, preference-aligned results.

Contribution

The work combines Schrödinger Bridge formulation with human-guided diffusion and iterative refinement to enhance medical image translation, ensuring boundary consistency and clinical preference alignment.

Findings

Outperforms prior methods in RMSE, SSIM, LPIPS, and Dice metrics.

Effectively suppresses shade artifacts while preserving structural details.

Requires only 10 sampling steps for high-quality results.

Abstract

We present a novel framework for CBCT-to-MDCT translation, grounded in the Schrodinger Bridge (SB) formulation, which integrates GAN-derived priors with human-guided conditional diffusion. Unlike conventional GANs or diffusion models, our approach explicitly enforces boundary consistency between CBCT inputs and pseudo targets, ensuring both anatomical fidelity and perceptual controllability. Binary human feedback is incorporated via classifier-free guidance (CFG), effectively steering the generative process toward clinically preferred outcomes. Through iterative refinement and tournament-based preference selection, the model internalizes human preferences without relying on a reward model. Subtraction image visualizations reveal that the proposed method selectively attenuates shade artifacts in key anatomical regions while preserving fine structural detail. Quantitative evaluations further demonstrate superior performance across RMSE, SSIM, LPIPS, and Dice metrics on clinical datasets -- outperforming prior GAN- and fine-tuning-based feedback methods -- while requiring only 10 sampling steps. These findings underscore the effectiveness and efficiency of our framework for real-time, preference-aligned medical image translation.