Abstract

Radiation Therapy (RT) plays a pivotal role in the treatment of cancer, offering the potential to effectively target and eliminate tumor cells while minimizing harm to surrounding healthy tissues. However, the success of RT heavily depends on meticulous treatment planning that ensures the optimal balance between delivering a sufficiently high dose to the tumor and sparing nearby critical organs. This critical process demands a multidisciplinary approach that combines medical expertise, advanced imaging techniques, and computational tools. Optimization techniques have emerged as indispensable tools in refining RT planning, enabling the precise adjustment of radiation beam arrangements and intensities to achieve treatment objectives while adhering to strict dose constraints. This study focuses on constrained optimization within RT Treatment Planning, utilizing metaheuristic algorithms to improve this process. The research compares three widely-used optimization techniques: Bat Search Optimization (BSO), Bacterial Foraging Algorithm (BFA), and Artificial Bee Colony (ABC). These metaheuristic approaches are evaluated against traditional methods, with evaluation metrics including execution time, convergence, and Dose-Volume Histogram (DVH) outcomes. The experimental results demonstrate that the metaheuristic techniques significantly outperform traditional methods. Among them, BFA delivers the most favorable results, offering minimal convergence time and superior DVH performance.

Statistics