(Sunday, 7/14/2019)
Room: ePoster Forums
Purpose: To investigate a hybrid automated treatment planning solution (HAP), which combines knowledge-based planning (KBP) and script-based planning, for esophageal cancer.
Methods: To fully investigate the advantage of the HAP, 3 planning strategies were implemented in this study, including HAP, KBP-only and full manual planning. Twenty patients were used to compare these three strategies. For HAP and KBP-only planning, the dose–volume histogram (DVH) estimation model was established by 70 esophageal patients. The objective function were generated by this model and inputted into a script-based automated planning system and traditional planning system for HAP and KBP-only planning, respectively. For full manual planning, clinical standards was used for treatment planning.
Results: Among all 3 strategies, HAP have the best performance on all indices except PTV dose homogeneity and Lung V5. Compare to KBP-only, HAP improved all indices except Lung V5. There was not improvement for KBP-only on OAR dose-volume indices. The spinal cord of the KBP-only even worse than manual planning. And PTV dose homogeneity was degraded by KBP-only planning. The most significant improvement for HAP was PTV conformity and max dose of spinal cord (p<0.001). Meanwhile the average planning time for HAP was 57 min, which was less than KBP-only (63 min) and full manually planning (118 min).
Conclusion: Hybrid automated treatment planning is an effective planning strategy for obtaining high quality treatment plan in esophageal cancer.
Keywords
Not Applicable / None Entered.
Taxonomy
IM- Radiation dose and risk: General (Most Aspects)
Contact Email
