Implementation of volumetric-modulated arc therapy for locally advanced breast cancer patients: Dosimetric comparison with deliverability consideration of planning techniques and predictions of patient-specific QA results via supervised machine learning.

PURPOSE: The aim of this study was to implement a clinically deliverable VMAT planning technique dedicated to advanced breast cancer, and to predict failed QA using a machine learning (ML) model to optimize the QA workload. METHODS: For three planning methods (2A: 2-partial arc, 2AS: 2-partial arc with splitting, 4A: 4-partial arc), dosimetric results were compared with patient-specific QA performed with the electronic portal imaging device of the linac. A dataset was built with the pass/fail status of the plans and complexity metrics. It was divided into training and testing sets. An ML metamodel combining predictions from six base classifiers was trained on the training set to predict plans as 'pass' or 'fail'. The predictive performances were evaluated using the unseen data of the testing set. RESULTS: The dosimetric comparison highlighted that 4A was the highest dosimetric performant method but also the poorest performant in the QA process. 2AS spared the best heart, but provided the highest dose to the contralateral breast and lowest node coverage. 2A provides a dosimetric compromise between organ at risk sparing and PTV coverage with satisfactory QA results. The metamodel had a median predictive sensitivity of 73% and a median specificity of 91%. CONCLUSIONS: The 2A method was selected to calculate clinically deliverable VMAT plans; however, the 2AS method was maintained when the heart was of particular importance and breath-hold techniques were not applicable. The metamodel provides promising predictive performance, and it is intended to be improved as a larger dataset becomes available.

Haute Couture or Ready-to-Wear? Tailored Pelvic Radiotherapy for Prostate Cancer Based on Individualized Sentinel Lymph Node Detection.

Prostate cancer (PCa) pelvic radiotherapy fields are defined by guidelines that do not consider individual variations in lymphatic drainage. We examined the feasibility of personalized sentinel lymph node (SLN)-based pelvic irradiation in PCa. Among a SLN study of 202 patients, we retrospectively selected 57 patients with a high risk of lymph node involvement. Each single SLN clinical target volume (CTV) was individually segmented and pelvic CTVs were contoured according to Radiation Therapy Oncology Group (RTOG) guidelines. We simulated a radiotherapy plan delivering 46 Gy and calculated the dose received by each SLN. Among a total of 332 abdominal SLNs, 305 pelvic SLNs (beyond the aortic bifurcation) were contoured (mean 5.4/patient). Based on standard guidelines, CTV missed 67 SLNs (22%), mostly at the common iliac level (40 SLNs). The mean distance between iliac vessels and the SLN was 11mm, and despite a 15mm margin around the iliac vessels, 9% of SLNs were not encompassed by the CTV. Moreover, 42 SLNs (63%) did not receive 95% of the prescribed dose. Despite a consensus on contouring guidelines, a significant proportion of SLNs were not included in the pelvic CTV and did not receive the prescribed dose. A tailored approach based on individual SLN detection would avoid underdosing pelvic lymph nodes that potentially contain tumor cells.