This study aimed to integrate Monte Carlo (MC) simulation with deep learning (DL)-based denoising techniques to achieve fast and accurate prediction of high-quality electronic portal imaging device (EPID) transmission dose (TD) for patient-specific quality assurance (PSQA). A total of 100 lung cases were used to obtain the noisy EPID TD by the ARCHER MC code under four kinds of particle numbers ( \(1\times 10^6\) , \(1\times 10^7\) , \(1\times 10^8\) and \(1\times 10^9\) ), and the original EPID TD was denoised by the SUNet neural network. The denoised EPID TD was assessed both qualitatively and quantitatively using the structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and gamma passing rate (GPR) with respect to \(1\times 10^9\) as a reference. The computation times for both the MC simulation and DL-based denoising were recorded. As the number of particles increased, both the quality of the noisy EPID TD and computation time increased significantly ( \(1\times 10^6\) : 1.12 s, \(1\times 10^7\) : 1.72 s, \(1\times 10^8\) : 8.62 s, and \(1\times 10^9\) : 73.89 s). In contrast, the DL-based denoising time remained at 0.13 \(-\) 0.16 s. The denoised EPID TD shows a smoother visual appearance and profile curves, but differences between \(1\times 10^6\) and \(1\times 10^9\) still remain. SSIM improves from 0.61 to 0.95 for \(1\times 10^6\) , 0.70 to 0.96 for \(1\times 10^7\) , and 0.90 to 0.97 for \(1\times 10^8\) . PSNR increases by > 20% for \(1\times 10^6\) and \(1\times 10^7\) , and > 10% for \(1\times 10^8\) . GPR improves from 48.47% to 89.10% for \(1\times 10^6\) , 61.04% to 94.35% for \(1\times 10^7\) , and 91.88% to 99.55% for \(1\times 10^8\) . The method that combines MC simulation with DL-based denoising for EPID TD generation can accelerate TD prediction and maintain high accuracy, offering a promising solution for efficient PSQA.
