ESTRO 2020 Abstract Book

S112 ESTRO 2020

Conclusion Plan approval can be automatically performed with a higher specificity for capturing plans that could be improved, than a manual check by a dosimetrist. We are currently clinically implementing this framework, such that automatically approved plans (expected to be around 85%) would not be manually checked at all, significantly improving efficiency. OC-0221 Clinical experience of automated SBRT planning with Constrained Hierarchical Optimization L. Hong 1 , Y. Zhou 1 , J. Yang 1 , J. Mechalakos 1 , M. Hunt 1 , J. Yang 1 , J. Yamada 1 , J. Deasy 1 , M. Zarepisheh 1 1 Memorial Sloan Kettering Cancer Center, Medical Physics, New York, USA Purpose or Objective To present our clinical experience with a fully automated approach to SBRT treatment planning using Expedited Constrained Hierarchical Optimization (ECHO) to improve plan efficiency and quality. Material and Methods From April 2017 to September 2019, 1492 patients underwent SBRT radiotherapy for paraspinal and other metastatic tumors with 1739 different ECHO produced plans. From October 2019, ECHO also produced plans for post-brachytherapy prostate patients receiving 25Gy in 5 fractions SBRT treatment. After contouring, a template plan using 9 IMRT fields was set up and sent to ECHO through an application program interface plug-in from the treatment planning system Eclipse®. The clinical criteria required by the institution to be always met were formulated as hard constraints (such as maximum dose, mean dose and dose-volume-histogram (DVH) constraints), were strictly enforced by the optimization. Other clinical criteria defined as “desired” (e.g., better PTV coverage, lower normal organs’ doses) were optimized as much as possible by solving sequential constrained optimization problems. A correction step incorporating leaf sequencing and scattering contributions into optimization, and smoothing fluence map of beams for delivery efficiency was in the final step of ECHO. Upon ECHO completion, the planner received an email indicating the plan was ready for review.

0.86 ± 0.06. All ECHO plans were delivered after passing intuitional quality assurance process. We are currently using ECHO to generate over 80 SBRT plans a week in our clinic.

Conclusion We successfully implemented a constrained hierarchial optimization method in our clinic for automated SBRT planning. ECHO has achieved the expected goals of producing consistently high quality clinical plans, in a reasonable time, that push normal tissue sparing as much as possible while respecting disease treatment goals. This has further resulted in an improved clinical workflow and shorter times between simulation and treatment in our clinic. We are working to expand use of the system to other disease sites. OC-0222 Deep Neural Network and Transfer Learning for DVH prediction in VMAT prostate treatments E.M. Ambroa Rey 1 , J. Pérez-Alija 2 , P. Gallego 2 1 Consorci Sanitari de Terrassa, Medical Physics Unit- Radiation Oncology, Terrassa, Spain ; 2 Hospital de la Santa Creu i Sant Pau, Medical Physics, Barcelona, Spain Purpose or Objective Volumetric modulated arc therapy (VMAT) has been used widely to provide highly conformal plans. However, treatment planning has increased in complexity and has become a time-consuming process. The purpose of this work is to establish a convolutional neural network (CNN) model for the prediction of rectum and bladder dose-volume histograms (DVH) in prostate patients treated with a VMAT technique. Material and Methods A total of 145 patients with intermediate or high-risk prostate cancer treated with simultaneous integrated boost (SIB) were selected for this study. The prescribed dose was 50.4 Gy and 70Gy in 28 fractions to the pelvic and prostate area, respectively. Data were split into two sets: 120 and 25 patients, respectively. Besides, the first set was partitioned in training, validation, and test, each with 100, 10, and 10 patients. The second set was used for final validation. We use transfer learning in combination with a VGG-16 network. VGG-16 is a deep CNN pre-trained with the

Results Among all the treated SBRT ECHO plans, 400 were for 24Gy in a single fraction, 1165 for 27Gy in three fractions, and the rest for various prescriptions doses with varied fractionations. Most plans were for paraspinal tumors with 174, 762 and 426 in cervical, thoracic and lumbosacral spine respectively. The median PTV size was 84 cc (range 7 - 633). The median time to produce one ECHO plan was 64 minutes (range 11-340), largely dependent on the field sizes. Over 90% of cases required just one run to produce a clinically accepted plan, the rest required additional run of ECHO with parameter tweak for physician special requests. All plans produced met or bettered the institutional clinical criteria. Excellent target coverage was achieved with PTV V100% averaged 93.0% ± 3.1% and PTV V95% averaged 98.2% ± 1.9%. ECHO plans were also highly conformal with Paddick Conformity Index averaged