ESTRO 2025 - Abstract Book

S1086

Clinical – Head & neck

ESTRO 2025

Memorial Hospital, Sun Yat-sen University and Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangzhou, China. 3 Research cooperation department, Shenzhen United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China Purpose/Objective: When to operate adaptive radiotherapy is a key pain spot for clinical application. This study presents the prospective clinical validation of a fully automated decision-making system for ART in nasopharyngeal carcinoma (NPC). Material/Methods: We proposed a full automated decision-making system based on auto-segmentation and auto-planning. Four patients treated with an integrated CT linear accelerator (uRT-linac 506c, Shanghai United Imaging Healthcare Co., Ltd., China) were prospective enrollment. After fan beam computed tomography (FBCT) scanning, the image was sent to the proposed system. The gross tumor volume (GTVp), cervical lymph nodes (GTVn), clinical target volumes (CTVs) and organs at risk (OARs), were generated by the auto-segmentation model. Then an auto-planning algorithm was used for new planning. A formula combine with morphological and dose metrics was used for decision making. The morphological metrics included the volume of GTVp, parotids, submandibular and the volume of CTV2 exceed external. The dose metrics included V95 of GTVp, CTV1, CTV2, GTVn, Dmax of brainstem, spinalcord and temporal lobe. The method of calculation was shown in Table 1. If the score was larger than 7.5, the patient need to execute ART next day. We calculated the dose metrics between original plan and ART plan, as well as the volume change in targets and OARs.