Direct Dual-Energy CT Material Decomposition using Model-based Denoising Diffusion Model

TL;DR

This paper introduces DEcomp-MoD, a novel deep learning approach that directly converts DECT projection data into material images, improving accuracy by incorporating spectral models and diffusion priors, and outperforming existing methods.

Contribution

The paper presents a model-based diffusion method for direct material decomposition from DECT projections, integrating spectral knowledge and diffusion priors for enhanced accuracy.

Findings

DEcomp-MoD outperforms state-of-the-art methods in synthetic DECT data.

The approach guarantees consistency with the spectral DECT model.

Results demonstrate potential for clinical application.

Abstract

Dual-energy X-ray Computed Tomography (DECT) constitutes an advanced technology which enables automatic decomposition of materials in clinical images without manual segmentation using the dependency of the X-ray linear attenuation with energy. However, most methods perform material decomposition in the image domain as a post-processing step after reconstruction but this procedure does not account for the beam-hardening effect and it results in sub-optimal results. In this work, we propose a deep learning procedure called Dual-Energy Decomposition Model-based Diffusion (DEcomp-MoD) for quantitative material decomposition which directly converts the DECT projection data into material images. The algorithm is based on incorporating the knowledge of the spectral DECT model into the deep learning training loss and combining a score-based denoising diffusion learned prior in the material image domain. Importantly the inference optimization loss takes as inputs directly the sinogram and converts to material images through a model-based conditional diffusion model which guarantees consistency of the results. We evaluate the performance with both quantitative and qualitative estimation of the proposed DEcomp-MoD method on synthetic DECT sinograms from the low-dose AAPM dataset. Finally, we show that DEcomp-MoD outperform state-of-the-art unsupervised score-based model and supervised deep learning networks, with the potential to be deployed for clinical diagnosis.