AI-Enhanced Analysis of Percentage Depth Dose Curves Along the Beam Axis of a Phantom Filled with Different Clinical PTO Objects: A Monte Carlo Geant4 Study

Abstract PurposeThis study investigates the behaviors of percentage depth dose (PDD) curves along the beam axis in a phantom filled with different clinical patient treatment objects (PTOs). By integrating Artificial Intelligence (AI) with Monte Carlo simulations using the Geant4 toolkit, the research aims to enhance the precision and efficiency of dose distribution modeling in radiotherapy. Design/Methodology/ApproachA water-equivalent phantom was modeled, incorporating various clinical PTOs such as bone, muscle, fat, lung tissue, and metallic implants. The phantom was irradiated with photon beams of 6 MV and 18 MV. AI algorithms were employed to optimize Monte Carlo simulations in Geant4, facilitating the analysis of energy deposition and the generation of PDD curves for different scenarios. FindingsThe study reveals that the composition and density of PTOs significantly influence the PDD curves, with high-density materials causing pronounced changes in dose distribution. AI-enhanced simulations provided deeper insights into the complex interplay between PTO composition and beam energy, improving the accuracy of dose predictions. The results showed excellent agreement with experimental data, validating the AI-optimized Geant4 simulations. Practical Implications The integration of AI in Monte Carlo simulations offers a robust tool for improving radiotherapy treatment planning. The ability to accurately model complex geometries and interactions ensures personalized and effective dose delivery, potentially enhancing patient outcomes. Originality/ValueThis study pioneers the application of AI in enhancing Monte Carlo simulations within the Geant4 toolkit for radiotherapy. The findings underscore the importance of AI-driven approaches in advancing the precision and efficiency of dose distribution modeling in complex clinical scenarios.