Long short-term memory networks for proton dose calculation in highly heterogeneous tissues.

PURPOSE: To investigate the feasibility and accuracy of proton dose calculations with artificial neural networks (ANNs) in challenging three-dimensional (3D) anatomies. METHODS: A novel proton dose calculation approach was designed based on the application of a long short-term memory (LSTM) network. It processes the 3D geometry as a sequence of two-dimensional (2D) computed tomography slices and outputs a corresponding sequence of 2D slices that forms the 3D dose distribution. The general accuracy of the approach is investigated in comparison to Monte Carlo reference simulations and pencil beam dose calculations. We consider both artificial phantom geometries and clinically realistic lung cases for three different pencil beam energies. RESULTS: For artificial phantom cases, the trained LSTM model achieved a 98.57% γ-index pass rate ([1%, 3 mm]) in comparison to MC simulations for a pencil beam with initial energy 104.25 MeV. For a lung patient case, we observe pass rates of 98.56%, 97.74%, and 94.51% for an initial energy of 67.85, 104.25, and 134.68 MeV, respectively. Applying the LSTM dose calculation on patient cases that were fully excluded from the training process yields an average γ-index pass rate of 97.85%. CONCLUSIONS: LSTM networks are well suited for proton dose calculation tasks. Further research, especially regarding model generalization and computational performance in comparison to established dose calculation methods, is warranted.

Accounting for Range Uncertainties in the Optimization of Combined Proton-Photon Treatments Via Stochastic Optimization.

PURPOSE: Proton treatment slots are a limited resource. Combined proton-photon treatments, in which most fractions are delivered with photons and only a few with protons, may represent a practical solution to optimize the allocation of proton resources over the patient population. We demonstrate how a limited number of proton fractions can be optimally used in multimodality treatments and address the issue of the robustness of combined treatments against proton range uncertainties. METHODS AND MATERIALS: Combined proton-photon treatments are planned by simultaneously optimizing intensity modulated radiation therapy and proton therapy plans while accounting for the fractionation effect through the biologically effective dose model. The method was investigated for different tumor sites (a spinal metastasis, a sacral chordoma, and an atypical meningioma) in which organs at risk (OARs) were located within or near the tumor. Stochastic optimization was applied to mitigate range uncertainties. RESULTS: In optimal combinations, proton and photon fractions deliver similar doses to OARs overlaying the target volume to protect these dose-limiting normal tissues through fractionation. Meanwhile, parts of the tumor are hypofractionated with protons. Thus, the total dose delivered with photons is reduced compared with simple combinations in which each modality delivers the prescribed dose per fraction to the target volume. The benefit of optimal combinations persists when range errors are accounted for via stochastic optimization. CONCLUSIONS: Limited proton resources are optimally used in combined treatments if parts of the tumor are hypofractionated with protons and near-uniform fractionation is maintained in serial OARs. Proton range uncertainties can be efficiently accounted for through stochastic optimization and are not an obstacle for clinical application.

Towards a generalised development of synthetic CT images and assessment of their dosimetric accuracy.

Background: The interest in generating "synthetic computed tomography (CT) images" from magnetic resonance (MR) images has been increasing over the past years due to advances in MR guidance for radiotherapy. A variety of methods for synthetic CT creation have been developed, from simple bulk density assignment to complex machine learning algorithms.Material and methods: In this study, we present a general method to determine simplistic synthetic CTs and evaluate them according to their dosimetric accuracy. It separates the requirements on the MR image and the associated calculation effort to generate a synthetic CT. To evaluate the significance of the dosimetric accuracy under realistic conditions, clinically common uncertainties including position shifts and Hounsfield lookup table (HLUT) errors were simulated. To illustrate our approach, we first translated CT images from a test set of six pelvic cancer patients to relative electron density (ED) via a clinical HLUT. For each patient, seven simplified ED images (simED) were generated at different levels of complexity, ranging from one to four tissue classes. Then, dose distributions optimised on the reference ED image and the simEDs were compared to each other in terms of gamma pass rates (2 mm/2% criteria) and dose volume metrics.Results: For our test set, best results were obtained for simEDs with four tissue classes representing fat, soft tissue, air, and bone. For this simED, gamma pass rates of 99.95% (range: 99.72-100%) were achieved. The decrease in accuracy from ED simplification was smaller in this case than the influence of the uncertainty scenarios on the reference image, both for gamma pass rates and dose volume metrics.Conclusions: The presented workflow helps to determine the required complexity of synthetic CTs with respect to their dosimetric accuracy. The investigated cases showed potential simplifications, based on which the synthetic CT generation could be faster and more reproducible.

Analytical incorporation of fractionation effects in probabilistic treatment planning for intensity-modulated proton therapy.

PURPOSE: We show that it is possible to explicitly incorporate fractionation effects into closed-form probabilistic treatment plan analysis and optimization for intensity-modulated proton therapy with analytical probabilistic modeling (APM). We study the impact of different fractionation schemes on the dosimetric uncertainty induced by random and systematic sources of range and setup uncertainty for treatment plans that were optimized with and without consideration of the number of treatment fractions. METHODS: The APM framework is capable of handling arbitrarily correlated uncertainty models including systematic and random errors in the context of fractionation. On this basis, we construct an analytical dose variance computation pipeline that explicitly considers the number of treatment fractions for uncertainty quantitation and minimization during treatment planning. We evaluate the variance computation model in comparison to random sampling of 100 treatments for conventional and probabilistic treatment plans under different fractionation schemes (1, 5, 30 fractions) for an intracranial, a paraspinal and a prostate case. The impact of neglecting the fractionation scheme during treatment planning is investigated by applying treatment plans that were generated with probabilistic optimization for 1 fraction in a higher number of fractions and comparing them to the probabilistic plans optimized under explicit consideration of the number of fractions. RESULTS: APM enables the construction of an analytical variance computation model for dose uncertainty considering fractionation at negligible computational overhead. It is computationally feasible (a) to simultaneously perform a robustness analysis for all possible fraction numbers and (b) to perform a probabilistic treatment plan optimization for a specific fraction number. The incorporation of fractionation assumptions for robustness analysis exposes a dose to uncertainty trade-off, i.e., the dose in the organs at risk is increased for a reduced fraction number and/or for more robust treatment plans. By explicit consideration of fractionation effects during planning, we demonstrate that it is possible to exploit this trade-off during optimization. APM optimization considering the fraction number reduced the dose in organs at risk compared to conventional probabilistic optimization neglecting the fraction number. CONCLUSION: APM enables computationally efficient incorporation of fractionation effects in probabilistic uncertainty analysis and probabilistic treatment plan optimization. The consideration of the fractionation scheme in probabilistic treatment planning reveals the trade-off between number of fractions, nominal dose, and treatment plan robustness.

Impact of respiratory motion on variable relative biological effectiveness in 4D-dose distributions of proton therapy.

BACKGROUND: Organ motion during radiation therapy with scanned protons leads to deviations between the planned and the delivered physical dose. Using a constant relative biological effectiveness (RBE) of 1.1 linearly maps these deviations into RBE-weighted dose. However, a constant value cannot account for potential nonlinear variations in RBE suggested by variable RBE models. Here, we study the impact of motion on recalculations of RBE-weighted dose distributions using a phenomenological variable RBE model. MATERIAL AND METHODS: 4D-dose calculation including variable RBE was implemented in the open source treatment planning toolkit matRad. Four scenarios were compared for one field and two field proton treatments for a liver cancer patient assuming (α∕ß)x = 2 Gy and (α∕ß)x = 10 Gy: (A) the optimized static dose distribution with constant RBE, (B) a static recalculation with variable RBE, (C) a 4D-dose recalculation with constant RBE and (D) a 4D-dose recalculation with variable RBE. For (B) and (D), the variable RBE was calculated by the model proposed by McNamara. For (C), the physical dose was accumulated with direct dose mapping; for (D), dose-weighted radio-sensitivity parameters of the linear quadratic model were accumulated to model synergistic irradiation effects on RBE. RESULTS: Dose recalculation with variable RBE led to an elevated biological dose at the end of the proton field, while 4D-dose recalculation exhibited random deviations everywhere in the radiation field depending on the interplay of beam delivery and organ motion. For a single beam treatment assuming (α∕ß)x = 2 Gy, D95% was 1.98 Gy (RBE) (A), 2.15 Gy (RBE) (B), 1.81 Gy (RBE) (C) and 1.98 Gy (RBE) (D). The homogeneity index was 1.04 (A), 1.08 (B), 1.23 (C) and 1.25 (D). CONCLUSION: For the studied liver case, intrafractional motion did not reduce the modulation of the RBE-weighted dose postulated by variable RBE models for proton treatments.