Enhancing Synthetic CT from CBCT via Multimodal Fusion: A Study on the Impact of CBCT Quality and Alignment

TL;DR

This study improves synthetic CT generation from CBCT by integrating preoperative CT data, showing that multimodal fusion enhances image quality especially when CBCT quality is low or well-aligned, with consistent results across datasets.

Contribution

The paper introduces a multimodal learning approach combining CBCT and preoperative CT to enhance synthetic CT quality, emphasizing the impact of alignment and CBCT quality.

Findings

Multimodal sCT outperforms unimodal methods.

Alignment and CBCT quality significantly influence sCT quality.

Results are reproducible on clinical datasets.

Abstract

Cone-Beam Computed Tomography (CBCT) is widely used for real-time intraoperative imaging due to its low radiation dose and high acquisition speed. However, despite its high resolution, CBCT suffers from significant artifacts and thereby lower visual quality, compared to conventional Computed Tomography (CT). A recent approach to mitigate these artifacts is synthetic CT (sCT) generation, translating CBCT volumes into the CT domain. In this work, we enhance sCT generation through multimodal learning, integrating intraoperative CBCT with preoperative CT. Beyond validation on two real-world datasets, we use a versatile synthetic dataset, to analyze how CBCT-CT alignment and CBCT quality affect sCT quality. The results demonstrate that multimodal sCT consistently outperform unimodal baselines, with the most significant gains observed in well-aligned, low-quality CBCT-CT cases. Finally, we demonstrate that these findings are highly reproducible in real-world clinical datasets.