Incorporating patient-specific prior clinical knowledge to improve clinical target volume auto-segmentation generalisability for online adaptive radiotherapy of rectal cancer: A multicenter validation.
Journal:
Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
PMID:
39675574
Abstract
BACKGROUND & PURPOSE: Deep learning (DL) based auto-segmentation has shown to be beneficial for online adaptive radiotherapy (OART). However, auto-segmentation of clinical target volumes (CTV) is complex, as clinical interpretations are crucial in their definition. The resulting variation between clinicians and institutes hampers the generalizability of DL networks. In OART the CTV is delineated during treatment preparation which makes the clinician intent explicitly available during treatment. We studied whether multicenter generalisability improves when using this prior clinical knowledge, the pre-treatment delineation, as a patient-specific prior for DL models for online auto-segmentation of the mesorectal CTV.