S1607
Physics - Autosegmentation
ESTRO 2026
Conclusion: TotalSegmentator demonstrated robust performance for automated dental contouring in children, accurately reproducing reference sextants with submillimetre agreement. Notably, the model, trained on cone-beam CT data and permanent dentition, generalised well to planning CT scans with primary and mixed dentitions, highlighting its robustness across modalities and developmental stages. These results suggest that this open-access tool can be highly valuable for prospective or large-scale retrospective studies evaluating dental dose, thereby supporting the development of age-specific dose constraints in paediatric radiotherapy planning and improving treatment individualisation. References: 1. Milgrom SA, van Luijk P, Pino R, et al. Salivary and Dental Complications in Childhood Cancer Survivors Treated With Radiation Therapy to the Head and Neck: A PENTEC Comprehensive Review. Int J Radiat Oncol Biol Phys. 2024;119(2):467-4812. Wasserthal, J., Breit, H.-C., Meyer, M.T., Pradella, M., Hinck, D., Sauter, A.W., Heye, T., Boll, D., Cyriac, J., Yang, S., Bach, M., Segeroth, M., 2023. TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiology: Artificial Intelligence3. F. Bolelli et al., "Segmenting the Inferior Alveolar Canal in CBCTs Volumes: The ToothFairy Challenge," in IEEE Transactions on Medical Imaging, vol. 44, no. 4, pp. 1890-1906, April 2025 Keywords: Radiotherapy, Dental, Deep learning
Digital Poster Highlight 4605
CT-based brain substructure segmentation in paediatric and young adult medulloblastoma: a feasibility study using MR-derived training labels Chelsea Sargeant 1 , Eliana Vasquez Osorio 1 , Angela Davey 1 , Denis Page 1 , Peter Sitch 2 , Marcel van Herk 1 , Ed Smith 2,1 , Shermaine Pan 3 , Martin McCabe 1 , Marianne Aznar 1 1 Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom. 2 Department of Proton Beam Therapy, The Christie NHS Foundation Trust, Manchester, United Kingdom. 3 Department of Clinical Oncology, The Christie NHS Foundation Trust, Manchester, United Kingdom Purpose/Objective Accurate delineation of brain substructures is crucial for studying the late effects of paediatric CNS tumours. While MRI is routinely used for contouring, treatment planning and dose calculation relies on CT. CT-based segmentation in children remains
Made with FlippingBook - Share PDF online