Cross-Modal Guidance for Fast Diffusion-Based Computed Tomography

TL;DR

This paper introduces a method to enhance diffusion-based CT reconstructions by integrating additional imaging modalities without retraining, significantly improving sparse-view neutron CT results using X-ray data.

Contribution

It proposes a novel cross-modal guidance approach that leverages auxiliary modality data without retraining the diffusion prior, enabling faster and better reconstructions in costly imaging scenarios.

Findings

Reconstruction quality improves with cross-modal guidance.

Method effectively handles imperfect side modality data.

Significant enhancement in sparse-view neutron CT reconstructions.

Abstract

Diffusion models have emerged as powerful priors for solving inverse problems in computed tomography (CT). In certain applications, such as neutron CT, it can be expensive to collect large amounts of measurements even for a single scan, leading to sparse data sets from which it is challenging to obtain high quality reconstructions even with diffusion models. One strategy to mitigate this challenge is to leverage a complementary, easily available imaging modality; however, such approaches typically require retraining the diffusion model with large datasets. In this work, we propose incorporating an additional modality without retraining the diffusion prior, enabling accelerated imaging of costly modalities. We further examine the impact of imperfect side modalities on cross-modal guidance. Our method is evaluated on sparse-view neutron computed tomography, where reconstruction quality is substantially improved by incorporating X-ray computed tomography of the same samples.