PlanAct: An eclipse scripting API-based module embedding clinical optimization strategies for automated planning in...

Area of Science:

• Radiation Oncology
• Medical Physics
• Cancer Treatment

Background:

• Manual intensity-modulated radiotherapy (IMRT) planning for locally advanced non-small cell lung cancer (LA-NSCLC) is resource-intensive.
• Current automated methods like RapidPlan often require manual adjustments for LA-NSCLC to meet clinical objectives.

Purpose of the Study:

• Develop and validate PlanAct, an Eclipse Scripting API (ESAPI)-based module for automated IMRT planning in LA-NSCLC.
• Compare PlanAct's performance against RapidPlan and existing clinical plans.

Main Methods:

• PlanAct was developed with modular functions to automate IMRT plan generation and optimization.
• Executed on 56 retrospective LA-NSCLC cases, evaluating plans against RapidPlan and clinical benchmarks using institutional quality metrics.
• Statistical analysis assessed differences in plan quality and dosimetric requirement fulfillment.

Main Results:

• PlanAct-optimized plans showed superior quality and better organ-at-risk sparing, especially for lungs (p < 0.001 for V20 and Dmean), compared to RapidPlan.
• Significantly fewer unmet clinical requirements with PlanAct (1 plan) versus RapidPlan (18 plans) and clinical plans (10 plans).
• PlanAct demonstrated superior dose distributions and hotspot control, even in complex anatomical cases.

Conclusions:

• PlanAct is an effective tool for optimizing automated IMRT planning in LA-NSCLC.
• Achieved plans comparable to or better than clinical standards, even in challenging patient cases.
• Its modular design shows potential for integration into future autonomous, patient-specific radiotherapy planning systems.