Development and evaluation of machine learning models for voxel dose predictions in online adaptive magnetic resonance guided radiation therapy

摘要

Purpose Daily online adaptive plan quality in magnetic resonance imaging guided radiation therapy (MRgRT) is difficult to assess in relation to the fully optimized, high quality plans traditionally established offline. Machine learning prediction models developed in this work are capable of predicting 3D dose distributions, enabling the evaluation of online adaptive plan quality to better inform adaptive decision‐making in MRgRT. Methods Artificial neural networks predicted 3D dose distributions from input variables related to patient anatomy, geometry, and target/organ‐at‐risk relationships in over 300 treatment plans from 53 patients receiving adaptive, linac‐based MRgRT for abdominal cancers. The models do not include any beam related variables such as beam angles or fluence and were optimized to balance errors related to raw dose and specific plan quality metrics used to guide daily online adaptive decisions. Results Averaged over all plans, the dose prediction error and the absolute error were 0.1?±?3.4?Gy (0.1?±?6.2%) and 3.5?±?2.4?Gy (6.4?±?4.3%) respectively. Plan metric prediction errors were ?0.1?±?1.5%, ?0.5?±?2.1%, ?0.9?±?2.2?Gy, and 0.1?±?2.7?Gy for V95, V100, D95, and Dsubmean/sub respectively. Plan metric prediction absolute errors were 1.1?±?1.1%, 1.5?±?1.5%, 1.9?±?1.4?Gy, and 2.2?±?1.6?Gy. Approximately 10% (25) of the plans studied were clearly identified by the prediction models as inferior quality plans needing further optimization and refinement. Conclusion Machine learning prediction models for treatment plan 3D dose distributions in online adaptive MRgRT were developed and tested. Clinical integration of the models requires minimal effort, producing 3D dose predictions for a new patient’s plan using only target and OAR structures as inputs. These models can enable improved workflows for MRgRT through more informed plan optimization and plan quality assessment in real time.