Novel knowledge-based treatment planning model for hypofractionated radiotherapy of prostate cancer patients |
| |
| Institution: | 1. Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California;2. Department of Radiation Oncology, University of California San Francisco, San Francisco, California;1. Department of Radiation Oncology, VU University Medical Center, De Boelelaan, Amsterdam, The Netherlands;2. Department of Epidemiology and Biostatistics, VU University Medical Center, De Boelelaan, Amsterdam, The Netherlands;1. Department of Radiation Medicine, MedStar Georgetown University Hospital, Washington, USA;2. Radboud University Medical Center, Nijmegen, The Netherlands;3. Department of Radiation Oncology and Molecular Radiation Sciences, The Johns Hopkins University, Baltimore, USA;4. Department of Radiotherapy, Istituto Nazionale Tumori Regina Elena, Roma, Italy;5. Philips Radiation Oncology Systems, Madison, USA;1. Department of Radiation Medicine, Georgetown University Hospital, Washington, USA;2. Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, USA |
| |
| Abstract: | PurposeTo demonstrate the strength of an innovative knowledge-based model-building method for radiotherapy planning using hypofractionated, multi-target prostate patients.Material and methodsAn initial RapidPlan model was trained using 48 patients who received 60 Gy to prostate (PTV60) and 44 Gy to pelvic nodes (PTV44) in 20 fractions. To improve the model's goodness-of-fit, an intermediate model was generated using the dose-volume histograms of best-spared organs-at-risk (OARs) of the initial model. Using the intermediate model and manual tweaking, all 48 cases were re-planned. The final model, trained using these re-plans, was validated on 50 additional patients. The validated final model was used to determine any planning advantage of using three arcs instead of two on 16 VMAT cases and tested on 25 additional cases to determine efficacy for single-PTV (PTV60-only) treatment planning.ResultsFor model validation, PTV V95% of 99.9% was obtained by both clinical and knowledge-based planning. D1% was lower for model plans: by 1.23 Gy (PTV60, CI = 1.00, 1.45]), and by 2.44 Gy (PTV44, CI = 1.72, 3.16]). OAR sparing was superior for knowledge-based planning: ΔDmean = 3.70 Gy (bladder, CI = 2.83, 4.57]), and 3.22 Gy (rectum, CI = 2.48, 3.95]); ΔD2% = 1.17 Gy (bowel bag, CI = 0.64, 1.69]), and 4.78 Gy (femoral heads, CI = 3.90, 5.66]). Using three arcs instead of two, improvements in OAR sparing and PTV coverage were statistically significant, but of magnitudes < 1 Gy. The model failed at reliable DVH predictions for single PTV plans.ConclusionsOur knowledge-based model delivers efficient, consistent plans with excellent PTV coverage and improved OAR sparing compared to clinical plans. |
| |
| Keywords: | Knowledge-based Automatic planning Machine learning Prostate radiotherapy |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
