A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter

Multi-source computed tomography (MSCT) significantly improves temporal resolution but suffers from severe forward and cross scatter artifacts. Software-based scatter correction methods avoid additional hardware costs and radiation dose; however, model-based methods struggle with high-order scatter estimation, while deep learning-based methods lack physical constraints. To address these limitations, we propose a neural-analytical fusion (NAF) scatter correction method. Specifically, first-order Compton and Rayleigh scatter are analytically estimated using a GPU-accelerated physics model-based method. For high-order scatter, the multi-step scattering process is reformulated as an equivalent single-step interaction, and an equivalent high-order cross-section prediction network (EHCP-Net) is embedded within the analytical model to enable fast and physically constrained estimation of high-order scatter. The proposed method is validated on simulated and real data under different scanning geometries. Compared to the state-of-the-art scatter correction methods, our method demonstrates higher correction accuracy and effectively suppresses high-frequency artifacts. In scatter distribution comparison experiments, it achieved a mean absolute percentage error (MAPE) of less than 3% relative to Monte Carlo (MC) simulations. In scatter correction experiments, it yielded mean absolute errors (MAE) below 20 HU on simulated data, and below 30 HU on real data. The proposed method achieves effective scatter correction with strong physical constraints for MSCT.