ESTRO 2025 - Abstract Book

S2483

Physics - Autosegmentation

ESTRO 2025

unknown. The current study investigates the feasibility and time gain of implementing online artificial intelligence (AI)-based delineations for prostate cancer at a 1.5 T MRI-Linac.

Material/Methods: Fifteen consecutive prostate cancer patients, treated to 60 Gy in 20 fractions at a 1.5 T MRI-Linac, were included in the current prospective study. The first five patients (Group 1) were treated using the standard contouring workflow for all fractions. The last ten patients (Group 2) were treated with the standard workflow for fractions 1 up to 3 (Group 2–Standard) and an AI-based workflow for the remaining fractions (Group 2-AI). AI delineations were delivered using an in-house developed AI inference service and an in-house trained nnU-Net model [1,2]. Standard and AI-based workflows are depicted in Figure 1.