A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition

2026-06-29

AI Summary

This work addresses the highly challenging task of material decomposition in dual-energy computed tomography (DECT) under sparse-view conditions, which suffers from strong nonlinearity and ill-posedness, making it difficult for existing methods to simultaneously model global structures and suppress noise. The authors formulate the problem as a sparsely regularized nonlinear least-squares optimization and propose DECT-DRNet, an iterative dual-domain optimization network. Within a deep unrolling framework, this method introduces—for the first time—a learnable adjoint Jacobian operator based on filtered back-projection (FBP) and designs a dual-domain Fourier convolutional residual block that integrates geometric features in the image domain with noise suppression in the frequency domain, enabling synergistic modeling of global and local characteristics. Experiments demonstrate that the proposed approach significantly improves material decomposition accuracy under sparse-view settings, effectively reduces artifacts, preserves structural details, and outperforms current deep learning-based methods.

Abstract

Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical imaging. While sparse-view acquisition can lower radiation exposure, it makes DECT material decomposition even more challenging, as the problem is nonlinear and ill-posed. Existing deep unrolling approaches generally do not explicitly incorporate the Jacobian operator induced by the nonlinear forward model, and their sparsity priors are still mainly built on conventional convolutions, which are insufficient for modeling global structural information. This study addresses the challenge of DECT multi-material decomposition in sparse-view settings by representing it as a sparse-regularized nonlinear least-squares problem. To solve it, we propose an iterative dual-domain refinement network (DECT-DRNet). In each iteration, the filtered back-projection (FBP)-based Jacobian approximation module is used first to generate an intermediate material decomposition result. Here, we characterize the forward process of material decomposition using a nonlinear operator, and then construct a theoretically grounded learnable approximation of the adjoint Jacobian operator by integrating the FBP algorithm with a U-Net into the backward process. In addition, to address the limitation of existing deep learning-based decomposition methods in globally suppressing noise and artifacts, we introduce a learnable sparse dual domain regularization term that incorporates Fourier convolutional residual blocks. This refinement block combines geometric feature extraction in the image domain with noise suppression in the frequency domain, allowing the model to capture both global and local features while maintaining structural details. DECT-DRNet demonstrates its ability to achieve more accurate material decomposition under sparse-view conditions.

Problem

• Dual-energy CT
• material decomposition
• sparse-view
• nonlinear inverse problem
• ill-posedness

Innovation

• Jacobian approximation
• dual-domain regularization
• Fourier convolution
• deep unrolling
• sparse-view DECT