Room: Stars at Night Ballroom 1
Purpose: We present our initial clinical experience with a fully automated approach to treatment planning based on a Pareto optimal, constrained hierarchical optimization algorithm, named ECHO(for Expedited-Constrained-Hierarchical-Optimization).
Methods: From 04/2017 to 10/2018, 523 patients underwent SBRT radiotherapy for paraspinal and other oligometastatic tumors with 640 different ECHO produced plans. 182 plans were for 24Gy in a single fraction, 387 plans for 27Gy in three fractions, and the rest for other prescriptions and/or fractionations. 84.5% plans were for paraspinal tumors with 69, 302 and 170 in cervical, thoracic and lumbosacral spine respectively. After contouring, a template plan using 9 IMRT fields based on disease site and tumor location was sent to ECHO through an application program interface plug-in from the treatment planning system. ECHO returned a Pareto-optimal plan that satisfied hard critical structure constraints with optimal target volume coverage and lowest achievable normal tissue doses. Upon ECHO completion, the planner received an email indicating the plan was ready for review. The plan was accepted if all clinical criteria were met, otherwise a limited number of parameters could be adjusted for another ECHO run.
Results: The median PTV size was 84.3 cc (range 6.9 - 633.2). The median time to produce one ECHO plan was 63.5 minutes (range 11-340), largely dependent on the field sizes. 79.7% of cases required one run to produce a clinically accepted plan, 13.3% required one additional run with minimal parameter adjustments, and 7.0% required two or more additional runs with significant parameter modification. All plans met or bettered the institutional clinical criteria.
Conclusion: ECHO produced high quality clinical plans, improved planning efficiency and enabled expedited treatment planning for SBRT paraspinal and other oligometastatic tumors in our clinic. Constrained hierarchical optimization is a powerful platform that can be further exploited for efficient, Pareto optimal, and automated IMRT planning.
Funding Support, Disclosures, and Conflict of Interest: This work was partially supported by the MSK Cancer Center Support Grant/Core Grant (P30 CA008748), and the Enid A. Haupt Endowed Chair Fund.
Not Applicable / None Entered.