Stereotactic radiosurgery is a minimally invasive procedure that uses a focused beam of radiation as an ablative instrument to destroy brain tumors. To deposit a high dose of radiation in a tumor, while reducing the dose to healthy tissue, a large number of beams are crossfired at the tumor from multiple directions. The treatment planning problem (also called the inverse dosimetry problem) is to compute a set of beams that produces the desired dose distribution. So far its investigation has focused on the generation of isocenter-based treatments in which the beam axes intersect at a common point, the isocenter. However this restriction limits the applicability of the treatments to tumors which have simple shapes. This paper describes CARABEAMER, a new treatment planner for a radiosurgical system in which the radiation source can be arbitrarily positioned and oriented by a six-degree-of-freedom manipulator. This planner uses randomized techniques to guess a promising initial set of beams. It then applies space partitioning and linear programming techniques to compute the energy to be delivered along each beam. Finally, it exploits the results of the linear program to iteratively adapt and improve the beam set. Experimental results obtained with CARABEAMER on both patient and synthetic cases are presented and discussed. These results demonstrate that a radiosurgical system with general kinematics can deliver treatments in which the region receiving a high dose closely matches the shape of the tumor, even in complicated cases. They also suggest new research directions which are discussed at the end of the paper.
View details for PubMedID 10710294