Adjust The Beam Direction In The Imrt Optimization Algorithm

Radiotherapy, together with the surgery and chemotherapy, are three main means for tumor treatment. It is a historic advancement for tumor treatment that the intensity-modulated radiotherapy (IMRT) replaces the classical three-dimensional (3D) conformal radiotherapy (3D-CRT). Because of the complicated clinical conditions, the IMRT planning still has many problems needed to be dealt with.Aiming at the clinical requirements, the studies in this paper focus on the problem of the beam angle optimization (BAO), which are briefly listed below:(1) An approaching genetic algorithm (AGA) based on the approaching concept which is derived from the particle swarm optimization (PSO) was proposed to automatically select beam angles. Approaching, serving as the main method to search, and some special updating strategies are designed to enhance the evolving ability of the algorithm. A simulated case and a clinical cancer were employed to demonstrate the feasibility of AGA. For the case investigated, AGA was feasible for BAO problem and converged faster than GA.(2) Based on the knowledge of biological DNA evolution, a novel DNA genetic algorithm (DNA-GA) was introduced to solve BAO problem. According to the phenomenon of mutation hot spots and cold spots in the biological DNA evolutionary process, a creative bit mutation operation was proposed. Accordingly, the deletion, insertion and inversion, which are happened in the biological DNA evolutionary process, were evolved to the deletion, insertion and inversion structure mutation operations in DNA-GA. These mutation operations changed the auxiliary status of mutation operations in genetic algorithm (GA) and enhance the evolving ability of DNA-GA effectively. The preliminary results demonstrated that DNA-GA was feasible for BAO problem and converged faster than GA.