ESTRO 2022 - Abstract Book

S647

Abstract book

ESTRO 2022

Conclusion The different attitudes in handling PTV dose coverage in RWB-TF reflects into mild/moderate differences in sparing ipsilateral lung between Institutes. Inter-institute variability in lung dose prediction appears to have no relevant dependence on patient's anatomy. This result, in addition to the limited variability between models in predicting ipsilateral lung DVH, suggests promising potential applications in multi-institutional benchmark models. This study is supported by an AIRC grant (IG23150).

PD-0734 Artificial Intelligence and Multi-Criteria Optimization for automatic treatment plan generation

J. Mazurier 1 , G. Sidorski 1 , X. Franceries 2 , I. Berry 3 , B. Pichon 1 , B. Pinel 1 , I. Latorzeff 1 , O. Gallocher 4 , G. Jimenez 1 , J. Camilleri 1 , V. Connord 1 , Y. Marty 1 , N. Mathy 1 , D. Zarate 1 1 Clinique Pasteur, radiotherapy, Toulouse, France; 2 Université Toulouse Sabatier 3, INSERM UMR1037, TOULOUSE, France; 3 CNRS, CERCO, TOULOUSE, France; 4 Clinique Pasteur, radiotherapy, toulouse, France Purpose or Objective In RayStation v11A® TPS, 3 methods are available to generate treatment plans: A Multi-Criteria Optimization (MCO) and two Artificial Intelligences (AI), a Machine Learning (ML) and a Deep Learning (DL) algorithm. The goal is to evaluate these advanced methods to automatize our clinical routine. Materials and Methods The ML is based on Atlas of Random Forest and the DL on a Fully Convolutional Neural Network . They generate a predicted dose distribution. The AI methods were both trained on local treatment plans database, then the obtained models were adjusted in a dedicated RaySearch module, RayLearner. The MCO algorithm generate treatment plans (from users constraints) were no optimization goals can be improved without deteriorating another: Optimal Pareto Plans. The chosen predicted dose distribution calculated from theorical fluence. Then, the three methods use the same Mimicking algorithm which transforms the predicted dose distribution into a deliverable treatment plan. Methods have been evaluated on prostate cancer treated at 78, 76 or 66 Gy, delivered with VMAT arcs of photons (6 or 10MV) on Novalis TX and Halcyon VARIAN®. We developed scripts to use MCO automatically and the AI algorithms were trained with 100 of our 78Gy treatment plans and they were adjusted in RayLearner to be used at 76 and 66Gy. Plans were clinically accepted when they fullfil the RECORAD recommendations and pass the Patient Quality Assurance Criteria: Gamma index > 1 for 95% of points in 3% 2mm, measured with ARCHECK (and/or EPID SunCheck system (SunNuclear) We compared MCO, ML and DL plans to manual Standard Optimized plans (SO) on 50 treatment plans with dosimetric Index: Conformity (C), Homogeneity (H) and Dose Gradient (DG). And the plan complexity were compared with the Modulation Complexity Score (MCS). We also evaluate the plan generation duration: active time (required by the user) and passive time (without the user). Results SO plans were clinically accepted with index : C ≈ 0.84, H ≈ 0.07, DG ≈ 3.11, MSC ≈ 0.35 and plans were generated in an average time of 180 active minutes. 80% of ML plans were accepted after 16 passive minutes and 85% of DL plans were accepted after 11 passive minutes. 100 % of others AI plans were accepted after additionnal optimization ( ≈ 5 active minutes). AI dose distributions were at least equivalent and more complex than SO: C ≈ 0.86, H ≈ 0.08, DG ≈ 3.02, MSC ≈ 0.31 100% of MCO plans were generated in 30 passive minutes and were after additionnal standard optimization ( ≈ 30 active minutes). MCO plans had the best and most complex dose distributions (C ≈ 0.87, H ≈ 0.06, DG ≈ 2.88, MSC ≈ 0.2) Conclusion Automated methods gives results more homogeneous and very close (DL / ML) or event better (MCO) than SO. Futhermore, calculation were 2(MCO) to 16 (DL) times faster. Finally, MCO seems to be more adapted to complex and unusual clinical cases and AI can be used on classical clinical cases which allows to consider adaptative radiotherapy.

PD-0735 Planning MV photons with dose-to-medium can be disruptive to traditional planning

D. Jurado-Bruggeman 1 , C. Muñoz-Montplet 1

1 Institut Català d’Oncologia - Girona, Medical Physics and Radiation Protection Department, Girona, Spain

Purpose or Objective Planning considerations were developed for previous generation calculation algorithms yielding dose to water-in-water (Dw,w). Advanced algorithms offer superior radiation transport accuracy, but their dose values in terms of dose to medium- in-medium (Dm,m) depend on the medium considered. This can be problematic in plan optimisation since a uniform photon fluence does not necessarily imply a uniform dose distribution. This work aims to show how trying to mimic traditional Dw,w planning with Dm,m can involve new clinical and robustness issues.

Materials and Methods