A deep-learning-based surrogate model for Monte-Carlo simulations of the linear energy transfer in primary brain tumor patients treated with proton-beam radiotherapy.
Sebastian StarkeAaron KieslichMartina PalkowitschFabian HenningsEsther G C TroostMechthild KrauseJona BensbergChristian HahnFeline HeinzelmannChristian BäumerArmin LührBeate TimmermannSteffen LoeckPublished in: Physics in medicine and biology (2024)
Objective. This study explores the use of neural networks (NNs) as surrogate models for Monte-Carlo (MC) simulations in predicting the dose-averaged linear energy transfer (LET d ) of protons in proton-beam therapy based on the planned dose distribution and patient anatomy in the form of computed tomography (CT) images. As LET d is associated with variability in the relative biological effectiveness (RBE) of protons, we also evaluate the implications of using NN predictions for normal tissue complication probability (NTCP) models within a variable-RBE context. Approach. The predictive performance of three-dimensional NN architectures was evaluated using five-fold cross-validation on a cohort of brain tumor patients ( n = 151). The best-performing model was identified and externally validated on patients from a different center ( n = 107). LET d predictions were compared to MC-simulated results in clinically relevant regions of interest. We assessed the impact on NTCP models by leveraging LET d predictions to derive RBE-weighted doses, using the Wedenberg RBE model. Main results. We found NNs based solely on the planned dose distribution, i.e. without additional usage of CT images, can approximate MC-based LET d distributions. Root mean squared errors (RMSE) for the median LET d within the brain, brainstem, CTV, chiasm, lacrimal glands (ipsilateral/contralateral) and optic nerves (ipsilateral/contralateral) were 0.36, 0.87, 0.31, 0.73, 0.68, 1.04, 0.69 and 1.24 keV µ m -1 , respectively. Although model predictions showed statistically significant differences from MC outputs, these did not result in substantial changes in NTCP predictions, with RMSEs of at most 3.2 percentage points. Significance. The ability of NNs to predict LET d based solely on planned dose distributions suggests a viable alternative to compute-intensive MC simulations in a variable-RBE setting. This is particularly useful in scenarios where MC simulation data are unavailable, facilitating resource-constrained proton therapy treatment planning, retrospective patient data analysis and further investigations on the variability of proton RBE.
Keyphrases
- monte carlo
- computed tomography
- deep learning
- energy transfer
- end stage renal disease
- data analysis
- neural network
- newly diagnosed
- dual energy
- ejection fraction
- contrast enhanced
- magnetic resonance imaging
- chronic kidney disease
- prognostic factors
- systematic review
- convolutional neural network
- case report
- positron emission tomography
- optical coherence tomography
- magnetic resonance
- climate change
- patient reported outcomes
- functional connectivity
- peritoneal dialysis
- machine learning
- radiation therapy
- radiation induced
- resting state
- emergency department
- cross sectional
- patient safety
- adverse drug
- cell therapy
- blood brain barrier
- cerebral ischemia