Enhancing Synthetic CT from CBCT via Multimodal Fusion and End-To-End Registration
Journal:
arXiv
Published Date:
Jul 8, 2025
Abstract
Cone-Beam Computed Tomography (CBCT) is widely used for intraoperative
imaging due to its rapid acquisition and low radiation dose. However, CBCT
images typically suffer from artifacts and lower visual quality compared to
conventional Computed Tomography (CT). A promising solution is synthetic CT
(sCT) generation, where CBCT volumes are translated into the CT domain. In this
work, we enhance sCT generation through multimodal learning by jointly
leveraging intraoperative CBCT and preoperative CT data. To overcome the
inherent misalignment between modalities, we introduce an end-to-end learnable
registration module within the sCT pipeline. This model is evaluated on a
controlled synthetic dataset, allowing precise manipulation of data quality and
alignment parameters. Further, we validate its robustness and generalizability
on two real-world clinical datasets. Experimental results demonstrate that
integrating registration in multimodal sCT generation improves sCT quality,
outperforming baseline multimodal methods in 79 out of 90 evaluation settings.
Notably, the improvement is most significant in cases where CBCT quality is low
and the preoperative CT is moderately misaligned.
