A dual-domain refinement network with FBP-based Jacobian learning for sparse-view dual-energy CT material decomposition

Tools

Liu, Qian and Fan, Xiaohong and Chen, (Ken) and Chen, Chong and Wang, Shuaikang and Zhang, Jianping (2026) A dual-domain refinement network with FBP-based Jacobian learning for sparse-view dual-energy CT material decomposition. IEEE Transactions on Computational Imaging. ISSN 2333-9403 (https://doi.org/10.1109/TCI.2026.3725929)

[thumbnail of Liu-etal-IEEE-TCI-2026-A-dual-domain-refinement-network-with-FBP-based-Jacobian-learning]
Preview
 Text. Filename: Liu-etal-IEEE-TCI-2026-A-dual-domain-refinement-network-with-FBP-based-Jacobian-learning.pdf
Accepted Author Manuscript
License: Creative Commons Attribution 4.0 logo
Download (3MB)| Preview

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 (DECTDRNet). In each iteration, the filtered back-projection (FBP)- based Jacobian approximation module is first used to generate an intermediate material decomposition result. Here, we characterize the forward model underlying 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 limited ability of existing deep learning-based decomposition methods to globally suppress noise and artifacts, we introduce a learnable sparse dual-domain regularization term that incorporates Fourier residual convolutional 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. In the sparseview setting with 60 projection views, DECT-DRNet improves the mean PSNR by 3.23 dB and 2.01 dB over classical DECT material decomposition methods on the breast spectral CT and abdominal CT datasets, respectively, demonstrating its ability to achieve more accurate material decomposition under sparse-view conditions. The corresponding qualitative results further show that DECT-DRNet effectively suppresses noise and artifacts.

ORCID iDs

Liu, Qian, Fan, Xiaohong, Chen, (Ken) ORCID logoORCID: https://orcid.org/0000-0002-6093-6623, Chen, Chong, Wang, Shuaikang and Zhang, Jianping;
CORE (COnnecting REpositories)