Modeling and Prediction of SIB Prostate IMRT Plans

Abstract

To use retrospective data from simultaneously integrated boost (SIB) prostate intensity modulated radiation therapy (IMRT) plans to model and optimize dose plan outcomes. Modeled outcomes could provide plan guidance for new cases and could also be used as a plan comparison tool. A nonlinear regression based model was developed to map distance to target histograms (DTH) for organs at risk (OARs) to their dose volume histograms (DVH). Contours of patients' planning target volumes (PTVs) and OARs were overlaid on CT image data to compute organ volumes and DTHs. For the training cohort, DVHs were extracted from the SIB PTV (58.8 - 70 Gy) and the OARs. Principle component analysis (PCA) was used to elicit the key feature correlations between the DTH and DVH curves. The initial model cohort consisted of 23 retrospective prostate SIB plans. A leave-one-out training scheme was followed to generate a predicted DVH for each plan. For 85% of the cases, the expert planned OAR DVHs either fell within the 68% confidence interval of the predicted DVH, or the model predicted that a lower dose could be delivered to the OARs. A regression based model was used to map patient anatomical features to OAR DVHs. Cases where the trained model differed significantly from the planned DVH can be further examined to evaluate plan integrity. The results are promising considering the small training set, and model robustness should improve with a larger training cohort. Future work will focus on comparing models trained locally to national planning data. Lung cases, along with head and neck cases will also be considered.