FOTELP-VOX-OA: Enhancing radiotherapy planning precision with particle transport simulations and Optimization Algorithms

Background and Objective

: Accurate tumor targeting with minimal exposure to healthy tissue remains a significant challenge in radiotherapy. Modern techniques like Intensity-Modulated Radiation Therapy and stereotactic radiotherapy increasingly rely on detailed simulations and planning to achieve maximum treatment efficiency. Particle transport simulations play a crucial role in accurately modeling interactions between radiation and biological structures, providing a foundation for advancements in treatment planning. Building on this, FOTELP-VOX-OA is introduced as a novel framework designed to determine the optimal external-beam radiotherapy treatment plan. The primary aim of this study is to integrate the existing FOTELP-VOX framework with various Optimization Algorithms, focusing on estimating the parameters of interest that lead to the optimal radiation dose. While the framework itself is not pathology-specific, ocular melanoma is chosen as a test case due to its requirement for exceptionally precise dose delivery, given the small tumor volume and proximity of critical ocular structures.

Methods:

Particle transport simulations were conducted with FOTELP-VOX software, enabling detailed dose distribution analysis in tissues. Simulated conditions included a detailed biological model of eye melanoma to closely mimic clinical scenarios. The study integrates advanced optimization algorithms, such as Random Search, Tree-structured Parzen Estimator, and Genetic Algorithm, into the FOTELP-VOX framework, creating FOTELP-VOX-OA, to achieve the optimal treatment plan. Additionally, a specialized metric named Total Error was developed to determine the efficiency of the proposed treatment plan, focusing on both the desired tumor dose and minimizing exposure to surrounding tissues.

Results:

In the presented case-study, FOTELP-VOX-OA, utilizing the Genetic Algorithm, achieved a Total Error of 1701.52, significantly improving treatment planning compared to a human expert. However, this approach required the longest computation time among all methods. In contrast, the Tree-structured Parzen Estimator within the FOTELP-VOX-OA framework provided a balanced trade-off between speed and accuracy, while the Random Search-based solution was the fastest but also the least accurate.

Conclusion:

The FOTELP-VOX-OA framework improves radiotherapy precision, reduces risks to surrounding healthy tissues, and achieves better treatment outcomes. This approach demonstrates how particle transport simulations, coupled with optimization techniques, can address critical challenges in radiotherapy planning, paving the way for future applications in other tumor sites and clinical contexts.