ESTRO 2024 - Abstract Book

S3047

Physics - Autosegmentation

ESTRO 2024

Keywords: autosegmentation, pelvic lymph node, validation

References:

1. Harris VA, Staffurth J, Naismith O, Esmail A, Gulliford S, Khoo V, Lewis R, Littler J, McNair H, Sadoyze A, Scrase C, Sohaib A, Syndikus I, Zarkar A, Hall E, Dearnaley D, PIVOTAL Trialists (2015) Consensus Guidelines and Contouring Atlas for Pelvic Node Delineation in Prostate and Pelvic Node Intensity Modulated Radiation Therapy. Int J Radiat Oncol Biol Phys 92:874–883. https://doi.org/10.1016/j.ijrobp.2015.03.021 2. Gooding MJ, Boukerroui D, Vasquez Osorio E, Monshouwer R, Brunenberg E (2022) Multicenter comparison of measures for quantitative evaluation of contouring in radiotherapy. Phys Imaging Radiat Oncol 24:152–158. https://doi.org/10.1016/j.phro.2022.11.009 3. Hall WA, Paulson E, Davis BJ, Spratt DE, Morgan TM, Dearnaley D, Tree AC, Efstathiou JA, Harisinghani M, Jani AB, Buyyounouski MK, Pisansky TM, Tran PT, Karnes RJ, Chen RC, Cury FL, Michalski JM, Rosenthal SA, Koontz BF, Wong AC, Nguyen PL, Hope TA, Feng F, Sandler HM, Lawton CAF (2021) NRG Oncology Updated International Consensus Atlas on Pelvic Lymph Node Volumes for Intact and Postoperative Prostate Cancer. Int J Radiat Oncol Biol Phys 109:174–185. https://doi.org/10.1016/j.ijrobp.2020.08.034

1334

Proffered Paper

Histology to CT transfer for HNC target volume auto-segmentation with deep-learning diffusion models

Amaury Leroy 1,2,3 , Alexandre Cafaro 1,2,3 , Nazim Benzerdjeb 4 , Anne Champagnac 5 , Grégoire Gessain 6 , Philippe Gorphe 7 , Daphné Morel 2 , Charlotte Robert 2 , Roger Sun 2 , Philippe Zrounba 8 , Vincent Lepetit 9 , Nikos Paragios 1 , Vincent Grégoire 3 , Eric Deutsch 2 1 Therapanacea, Artificial Intelligence, Paris, France. 2 Institut Gustave Roussy, Paris-Saclay University, Inserm 1030, Molecular Radiotherapy and Therapeutic Innovation, Villejuif, France. 3 Centre Léon Bérard, Radiation Oncology, Lyon, France. 4 University Hospital of Lyon, Pathology, Lyon, France. 5 Centre Léon Bérard, Pathology, Lyon, France. 6 Institut Gustave Roussy, Paris-Saclay University, Pathology, Villejuif, France. 7 Institut Gustave Roussy, Paris-Saclay University, Surgery, Villejuif, France. 8 Centre Léon Bérard, Surgery, Lyon, France. 9 Ecole des Ponts ParisTech, CNRS, Marne-la Vallée, France

Purpose/Objective:

The precise delineation of target volumes in radiotherapy (RT) planning is crucial for effective tumor irradiation while protecting adjacent healthy tissues. In the head and neck (H&N) region, where the tumor's proximity to critical structures such as cartilage, salivary glands, or muscles involved in swallowing and phonation, inaccuracies can have dramatic consequences for patient outcomes. The challenge culminates due to experts' varying interpretations of imaging data, caused by factors like image quality, physician's expertise, and motion artifacts. This variability can lead to inconsistencies in treatment plans and increases the risk of side effects or reduced tumor control probability.