Towards automated on-line adaptation of 2-Step IMRT plans: QUASIMODO phantom and prostate cancer cases

Background: The standard clinical protocol of image-guided IMRT for prostate carcinoma introduces isocenter relocation to restore the conformity of the multi-leaf collimator (MLC) segments to the target as seen in the cone-beam CT on the day of treatment. The large interfractional deformations of the clinical target volume (CTV) still require introduction of safety margins which leads to undesirably high rectum toxicity. Here we present further results from the 2-Step IMRT method which generates adaptable prostate IMRT plans using Beam Eye View (BEV) and 3D information. Methods: Intermediate/high-risk prostate carcinoma cases are treated using Simultaneous Integrated Boost at the Universitatsklinkum Wurzburg (UKW). Based on the planning CT a CTV is defined as the prostate and the base of seminal vesicles. The CTV is expanded by 10 mm resulting in the PTV; the posterior margin is limited to 7 mm. The Boost is obtained by expanding the CTV by 5 mm, overlap with rectum is not allowed. Prescription doses to PTV and Boost are 60.1 and 74 Gy respectively given in 33 fractions. We analyse the geometry of the structures of interest (SOIs): PTV, Boost, and rectum, and generate 2-Step IMRT plans to deliver three fluence steps: conformal to the target SOIs (S0), sparing the rectum (S1), and narrow segments compensating the underdosage in the target SOIs due to the rectum sparing (S2). The width of S2 segments is calculated for every MLC leaf pair based on the target and rectum geometry in the corresponding CT layer to have best target coverage. The resulting segments are then fed into the DMPO optimizer of the Pinnacle treatment planning system for weight optimization and fine-tuning of the form, prior to final dose calculation using the collapsed cone algorithm. We adapt 2-Step IMRT plans to changed geometry whilst simultaneously preserving the number of initially planned Monitor Units (MU). The adaptation adds three further steps to the previous isocenter relocation: 1) 2-Step generation for the geometry of the day using the relocated isocenter, MU transfer from the planning geometry; 2) Adaptation of the widths of S2 segments to the geometry of the day; 3) Imitation of DMPO fine-tuning for the geometry of the day. Results and conclusion: We have performed automated 2-Step IMRT adaptation for ten prostate adaptation cases. The adapted plans show statistically significant improvement of the target coverage and of the rectum sparing compared to those plans in which only the isocenter is relocated. The 2-Step IMRT method may become a core of the automated adaptive radiation therapy system at our department.