MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Automated SBRT Planning Using Constrained Hierarchical Optimization: Three Year Clinical Experience with Over 1900 Patients

L Hong*, Y Zhou, Q Huang, J Yang, H Pham, J Mechalakos, M Hunt, J Deasy, M Zarepisheh, Memorial Sloan Kettering Cancer Center, New York, NY

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose: present our clinical experience with an automated approach to SBRT treatment planning using expedited constrained hierarchical optimization (ECHO) integrated with Eclipse® treatment planning system through application program interface (API) interface.

Methods: April 2017 to February 2020, 1962 patients underwent SBRT radiotherapy using 2215 ECHO produced plans. Plans included 1725 paraspinal tumors, 468 other metastatic tumors and 22 prostate patients. After contouring, a template using 9 IMRT fields was created and sent to ECHO through the Eclipse API plug-in. ECHO produced a Pareto optimal plan that satisfied hard clinical constraints with optimal target coverage and normal tissue doses as low as possible. Upon ECHO completion, the planner received an email indicating the plan was ready for review. The plan was accepted by the planner if all clinical criteria were met, otherwise a limited number of parameters could be adjusted prior to another run with ECHO.

Results: all treated ECHO plans, 431 were for 24 Gy in a single fraction, 1476 for 27 Gy in three fractions, and the rest for various prescriptions and fractionations. The median PTV size was 84 cc (range 3 - 633). The median time to produce one ECHO plan was 61 minutes (range 12 - 398), largely dependent on field size. All plans met or bettered the institutional clinical criteria. All ECHO plans were delivered after passing intuitional quality assurance process. ECHO is currently used to generate over 80 SBRT plans a week.

Conclusion: successfully implemented a constrained hierarchical optimization method in our clinic for automated SBRT planning using API scripting. ECHO improved consistency of plan quality for SBRT planning and shortened planning time by one day between simulation and treatment in our clinic.

Funding Support, Disclosures, and Conflict of Interest: This research was funded in part through the NIH/NCI Cancer Center Support Grant P30 CA008748, and the Enid A. Haupt Endowed Chair Fund. The authors have a patent application pending relevant to this report.

Keywords

Optimization, Treatment Planning

Taxonomy

TH- External Beam- Photons: Treatment planning using machine learning/Knowledge Based Planning/automation

Contact Email