Contour uncertainty assessment for MD-omitted daily adaptive online head and neck radiotherapy.

Background and purpose: Daily online adaptive radiotherapy (DART) increases treatment accuracy by crafting daily customized plans that adjust to the patient's daily setup and anatomy. The routine application of DART is limited by its resource-intensive processes. This study proposes a novel DART strategy for head and neck squamous cell carcinoma (HNSCC), automizing the process by propagating physician-edited treatment contours for each fraction.

Materials and methods: This study retrospectively analyzed 24 HNSCC patients treated with DART, encompassing 810 fractions. Both weekly and daily offline editing of the contours were emulated, propagating them to subsequent fractions using rigid and deformable image registration (DIR), respectively. Contour margins (CM) of 1, 2, and 3 mm were applied to create an adaptive gross tumor volume (aGTV) /adaptive clinical target volume (aCTV). Geometric coverage of the aGTV/aCTV relative to the ground-truth GTV/CTV were assessed. Additionally, adaptive dose distributions were predicted based on the aGTV/aCTV, and the dosimetric coverage of these predictions on the ground-truth GTV/CTV was evaluated. The recommended CM was identified by comparing the geometric and dosimetric accuracy across different combinations of CM, registration methods, and contour update frequencies.

Results: Rigid registration failed to accurately propagate most targets, even with a 3 mm CM. With DIR and a 2 mm CM, weekly or daily contour propagation achieved ≥ 98 % geometric coverage for gross tumor/nodal targets and ≥ 94 % for small suspicious nodes. DIR with weekly and daily contours achieved target dose coverage: V95% ≥ 99 % and V100% ≥ 95 % to the aGTV.

Conclusion: This study shows that DIR can effectively propagate periodically edited treatment contours for HNSCC patients, provided the correct CM is used. By adjusting contours weekly offline and using DIR at the console, the need for daily physician attendance can be eliminated.