ESTRO 2025 - Abstract Book

S3148

Physics - Inter-fraction motion management and offline adaptive radiotherapy

ESTRO 2025

The qSOP (Figure 1) classified plans as optimal if they met target coverage thresholds (LR-CTV≥99%, HR-CTV≥99.8%), with lower LR-CTV coverage (≥95%) sometimes allowed. Among valid plans, the one minimizing bowel irradiation was selected unless substantial bladder sparing could be achieved. With U-Seg3 embedded in the qSOP, optimal and acceptable plans were automatically selected in 46/60 and 56/60 cases (in line with clinical practice).

A mock-up of the tool and example U-Seg3 segmentation is shown in Figure 2. All structures and coverage statistics can be visualised, enabling observers to efficiently interpret the results.

Conclusion: U-Seg3 outperforms U-Seg1 and all known CBCT-based segmentation models of the female pelvis both in terms of scope and accuracy 3,4 . The plan assessment tool combining U-Seg3 and the qSOP identifies optimal plans with equivalent accuracy as two specially-trained observers, and could be used to reduce human resource requirements and promote broader adoption of POTD adaptive RT for LACC.