ESTRO 2020 Abstract Book

S781 ESTRO 2020

field isodose was extracted from the plan as physical points in the pCT space. We assumed that the pCT field configuration had the same physical positions in rCT space. From each point in the isodose, WEPL was calculated as the sum of linearly interpolated values, at each step along the opposite beam direction, until the edge of the image. The in-house WEPL program calculated isodose levels of 15%, 25%, 35%, 45% and 55% of the target dose, which were compared using Dice similarity coefficient to isodose levels created using the CERR platform in Matlab (Figure 1c/d). For the treatment planning calculations, a cube of size 20cmx20cmx20cm with the Hounsfield units (HUs) of water was created in Eclipse TPS with a cylindrical target in the middle. Two multi-field optimised proton plans were created with a target dose of 78 Gy. Plan 1 had fields at zero and 270 degrees and Plan 2 had fields at 270 and 325 degrees. The plans were recalculated on the same cube, where one and/or two inserts were created with HUs of either bone (300 HU), air (-1000 HU) or water (0 HU) in front of each field (Figure 1a/b). In total, each plan was re-calculated eight times.

Conclusion WEPL calculations compared to dose re-calculation using Eclipse TPS show promising results, especially for low isodose levels and small density changes. However further studies are needed to investigate how WEPL calculations can be used for higher isodose levels and more pronounced density changes. PO-1462 Automated robust planning for IMPT in oropharyngeal cancer patients using machine learning M. Huiskes 1 , R.G.J. Kierkels 1 , I.G. Van Bruggen 1 , M. Holmström 2 , H. Gruselius 2 , A. Fredriksson 2 , K. Berggren 2 , S. Both 1 , J.A. Langendijk 1 , F. Löfman 2 , E.W. Korevaar 1 1 University Medical Center Groningen, Radiation Oncology, Groningen, The Netherlands ; 2 RaySearch Laboratories, Machine Learning, Stockholm, Sweden Purpose or Objective Intensity modulated proton therapy (IMPT) uses multiple beams with steep in-field dose gradients and is therefore very sensitive for density and setup errors. Mathematical robust planning (RP) methods have been developed to account for these errors. However, RP methods take multiple scenario dose distributions into account during the optimization process, which makes RP generally slow as compared to margin-based planning methods. In this study, we developed and combined a Machine Learning Optimization (MLO) planning algorithm with a robust dose mimicking optimization algorithm to automatically create robust IMPT plans. We aimed to automatically generate robust IMPT plans with at least comparable target coverage robustness as clinically available robust IMPT plans for oropharyngeal cancer patients. Material and Methods In this study, robustly optimized IMPT plans of 65 HNC patients from our clinical and research archives were included. Dose distributions, contours, and CT image features of 60 patients were used to train a model to predict dose distributions for novel patients. Dose prediction was based on a random forest model with 96 trees at depth 10 including a conditional random field optimization. The target coverage during training were based on the primary and elective PTV. The predicted dose was converted to a deliverable plan using robust voxel- wise dose mimicking optimization, accounting for target robustness of 5 mm setup error and ±3% density uncertainty. The remaining five patients were used for validation of the MLO method. The beam configuration was copied from the clinical plans. Target robustness was assessed by a multi-scenario plan evaluation method comprising 16 dose recalculations with 8 positional isocenter shifts of 5 mm and a ±3% density uncertainty. The scenario dose distributions were combined into a voxel-wise minimum (vw-min) dose distribution and evaluated using the D 98% >94% criteria. In addition, we evaluated the spinal cord (D max <5400cGy), external D mean

Results The WEPL-based isodose levels were most similar to the full-fledged dose calculation for isodose levels of 15%, 25% and 35% with a median Dice value of 0.99 (range: 0.98- 1.00) across all scenarios and plans. The largest difference between the two plans occurred for an isodose level of 55%, due to different volume sizes of the isodoses. Plan 2 had a median Dice value of 0.94 (range: 0.72-0.98) and Plan 1 had a median Dice value of 0.76 (range: 0.55-0.93) (Figure 2). When an insert of bone were placed in front of each field, a median Dice value of 0.94 (range: 0.87-0.98) across both plans and all fields were calculated, while the median Dice value was 0.79 (range: 0.66-0.94), for an insert of air in front of each field.