Autori »
Lista completa degli autori
Area tematica
Sviluppo di tecnologie e dispositivi per la salute
Abstract
Purpose:To investigate a genetic algorithm approach to automatic treatment planning.
Methods: A Python script based on genetic algorithm (GA) was implemented for VMAT treatment planning of prostate tumor. The script was implemented in RayStation (RaySearch Laboratories AB, Stockholm, Sweden) treatment planning system using Python code. Two different clinical prescriptions were considered: 78 Gy prescribed to planning target volume (PTV) in 39 fractions (CASE 1) and simultaneous integrated boost (SIB) (70.2 Gy to prostate bed and 61.1 Gy to seminal vesicles) in 26 fractions (CASE 2). The script automatically creates beams, prescription doses, auxiliary regions of interest (ROIs) and optimizes doses to PTV and OARs according to genetic algorithm. A comparison with corresponding plans created with Monaco TPS (M, Elekta) and Auto-Planning module of Pinnacle3 (AP, Philips Medical System) was carried out. The plans were evaluated with a total score (TS) of PlanIQ (Sun Nuclear) in terms of target coverage and sparing of organ at risks as well as clinical score (CS) performed by a well trained Radiation Oncologist.
Results: In CASE 1, for four patients out of five, Auto-Planning had highest total score (TS) with really minimal difference with GA; mean value of TS were 150.6±30.7, 146.3±36.1 and 137.4±35.7 for AP, GA and M respectively. In terms of CS, the highest value has been attributed to GA in four patients out of five. For CASE 2, values of TS were higher for GA in three out of five patients whereas for the remaining plans AP was better. Mean value for TS were 163.5±16.8, 163.4±24.7 and 162.9±16.6 for AP, GA and M respectively. No significance differences were reported from ANOVA’s test for all considered parameters including CS.
Conclusion: This preliminary study shows that it is feasible to use the heuristic approach for plan generation in the context of VMAT prostate treatment planning and confirms that Pinnacle3 Auto-Planning (AP) is a commercial solution for automatic planning that provides very good results in terms of plan quality and robust automation. Studies are underway to determine whether GA can be used in other sites, as it appears to be a promising tool for automated inverse planning.
Autori
Claudio Vecchi tecnologie avanzate srl torino italy
Alessandro Alparone tecnologie avanzate srl torino italy
Christian Fiandra medical physics unit, a.o.u. città della salute e della scienza, torino italy
Elena Gallio department of oncology, radiation oncology, university of turin torino italy
Gabriella Balestra department of electronics and telecommunication, politecnico di torino torino italy
Riccardo Ragona department of oncology, radiation oncology, university of turin torino italy
Umberto Ricardi department of oncology, radiation oncology, university of turin torino italy
