Automating the treatment planning process for 3D-conformal pediatric craniospinal irradiation therapy

PurposePediatric patients with medulloblastoma in low- and middle-income countries (LMICs) are most treated with 3D-conformal photon craniospinal irradiation (CSI), a time-consuming, complex treatment to plan, especially in resource-constrained settings. Therefore, we developed and tested a 3D-conformal CSI autoplanning tool for varying patient lengths. Methods and materialsAutocontours were generated with a deep learning model trained:tested (80:20 ratio) on 143 pediatric medulloblastoma CT scans (patient ages: 2-19 years, median = 7 years). Using the verified autocontours, the autoplanning tool generated two lateral brain fields matched to a single spine field, an extended single spine field, or two matched spine fields. Additional spine subfields were added to optimize the corresponding dose distribution. Feathering was implemented (yielding nine to 12 fields) to give a composite plan. Each planning approach was tested on six patients (ages 3-10 years). A pediatric radiation oncologist assessed clinical acceptability of each autoplan. ResultsThe autocontoured structures' average Dice similarity coefficient ranged from .65 to .98. The average V95 for the brain/spinal canal for single, extended, and multi-field spine configurations was 99.9% +/- 0.06%/99.9% +/- 0.10%, 99.9% +/- 0.07%/99.4% +/- 0.30%, and 99.9% +/- 0.06%/99.4% +/- 0.40%, respectively. The average maximum dose across all field configurations to the brainstem, eyes (L/R), lenses (L/R), and spinal cord were 23.7 +/- 0.08, 24.1 +/- 0.28, 13.3 +/- 5.27, and 25.5 +/- 0.34 Gy, respectively (prescription = 23.4 Gy/13 fractions). Of the 18 plans tested, all were scored as clinically acceptable as-is or clinically acceptable with minor, time-efficient edits preferred or required. No plans were scored as clinically unacceptable. ConclusionThe autoplanning tool successfully generated pediatric CSI plans for varying patient lengths in 3.50 +/- 0.4 minutes on average, indicating potential for an efficient planning aid in a resource-constrained settings.