A Treatment Planning Optimization Method Based On Expert Plan Database For γ Ray Stereotactic Radiotherapy

Gamma Knife is a medical procedure that is used to treat several types of intracranial disease. The system utilizes gamma rays from Cobalt-60 radiation sources focused at an isocenter and a stereotactic frame system that serves as an immobilization device coordinate system. Treatment is performed by localizing the patient’s disease with a medical imaging study and positioning the diseased area at the focused intersection of the beams. Patient treatment may require multiple treatment positions and varying beam sizes. The treatment position, time, and beam size is determined through a treatment planning process. Traditionally Gamma Knife treatment planning is performed manually by an expert planner. This process can be time consuming and arrival at an optimal plan may depend on the skill of the planner.This work developed a new planning optimization based expert-knowledge database for gamma ray stereotactical radiotherapy.A patient plan database of the excellent historical cases is first built. Through data mining techniques, a most similar case in database is identified then, and the plan parameters of this historical case was set to be the initial solution of planning opitimization for the new patient. Finally the dose weight of all focuses is optimized with mixed integer programming.A software module is built by C++ programming. A expert plan database was created with 194 treatment plans for intracranial tumors. The module was tested using simulating clinical cases by match index MI, under-treatment ratio UTR, over-treatment ratio OTR, and proposed conformity index PCI.When the MI of input case and historical case was less than 1.3, it was able to automatically generate high quality treatment plan of which UTR was about 89% and PCI about 82%. Otherwise, the quality of the generated plan was worse of which UTR was only about 80 and PCI only aboutl%.The proposed method can automatically generate plans, and can save planning time siginificantly. Its plan quality is related to the number of cases in the database, more cases mean better plan quality.