Dual-Domain deep prior guided sparse-view CT reconstruction with multi-scale fusion attention.
Authors
Affiliations (7)
Affiliations (7)
- School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China.
- School of Medical Information and Engineering, Southwest Medical University, 646000, Luzhou, China.
- Chongqing Engineering Research Center of Medical Electronics and Information Technology, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China.
- Key Laboratory of Intelligent Computing for Advanced Manufacturing, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China.
- School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.
- Department of Electronic and Electrical Engineering, College of Engineering Design and Physical Sciences, Brunel University London, UB8 3PH, Uxbridge, UK.
- Chongqing Engineering Research Center of Medical Electronics and Information Technology, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China. [email protected].
Abstract
Sparse-view CT reconstruction is a challenging ill-posed inverse problem, where insufficient projection data leads to degraded image quality with increased noise and artifacts. Recent deep learning approaches have shown promising results in CT reconstruction. However, existing methods often neglect projection data constraints and rely heavily on convolutional neural networks, resulting in limited feature extraction capabilities and inadequate adaptability. To address these limitations, we propose a Dual-domain deep Prior-guided Multi-scale fusion Attention (DPMA) model for sparse-view CT reconstruction, aiming to enhance reconstruction accuracy while ensuring data consistency and stability. First, we establish a residual regularization strategy that applies constraints on the difference between the prior image and target image, effectively integrating deep learning-based priors with model-based optimization. Second, we develop a multi-scale fusion attention mechanism that employs parallel pathways to simultaneously model global context, regional dependencies, and local details in a unified framework. Third, we incorporate a physics-informed consistency module based on range-null space decomposition to ensure adherence to projection data constraints. Experimental results demonstrate that DPMA achieves improved reconstruction quality compared to existing approaches, particularly in noise suppression, artifact reduction, and fine detail preservation.