A Hybrid Cone-Beam CT Scatter Correction Method Combining Fast Monte-Carlo Simulation and Deep Neural Network

X-ray scatter presents a significant challenge in computed tomography (CT) by introducing artifacts and diminishing contrast, ultimately affecting measurement accuracy in reconstructed images. While Monte Carlo (MC) simulation is the gold standard for scatter correction, its high computational cost limits clinical applications. Accelerated MC methods improve efficiency but may compromise accuracy. Scatter kernel-based approaches allow quick implementation but lack precision in measurement. Deep learning-based methods show promising results but require thorough evaluation for generalizability across diverse imaging protocols. This study presents a hybrid scatter correction method for cone-beam CT (CBCT) that integrates fast MC simulation with a deep neural network, aiming to enhance measurement precision and efficiency. Fast MC simulations are employed for low-dose, sparse-view scatter estimations, serving as references…