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

2025-07-23

AI Summary

In dual-energy CT material decomposition, conventional image-domain post-processing methods neglect beam-hardening effects, limiting quantitative accuracy. This work proposes an end-to-end deep learning framework that directly reconstructs material-specific images from dual-energy projection data. Methodologically, we embed the spectral CT physical model into the diffusion model’s training objective to construct a model-driven score-based denoising diffusion prior; further, we design a physics-constrained conditional inference mechanism that introduces a learnable prior in the material image domain and jointly optimizes reconstruction consistency. Evaluated on the low-dose AAPM dataset, our method significantly outperforms existing unsupervised diffusion models and supervised deep networks, achieving high-accuracy, robust quantitative material decomposition. The approach demonstrates strong potential for clinical translation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Direct material decomposition from DECT projection data
• Overcome beam-hardening effect in image-domain methods
• Improve accuracy for clinical diagnosis applications

Innovation

• Direct DECT projection to material conversion
• Model-based diffusion with spectral knowledge
• Sinogram-consistent conditional diffusion optimization