Deep-Learning for Rapid Estimation of the Out-of-Field Dose in External Beam Photon Radiation Therapy – A Proof of Concept

Nathan Benzazon (1) , Alexandre Carré (1) , François de Kermenguy (1) , Stéphane Niyoteka (1) , Pauline Maury (1) , Julie Colnot (1) , Meissane M'Hamdi (1) , Mohammed El Aichi (1) , Cristina Veres (1) , Rodrigue Allodji (1) , Florent de Vathaire (1) , David Sarrut (2, 3) , Neige Journy (1) , Claire Alapetite (4) , Vincent Grégoire (5) , Eric Deutsch (1) , Ibrahima Diallo (1) , Charlotte Robert (1)

1 RaMo-IT - Radiothérapie Moléculaire et Innovation Thérapeutique
2 CREATIS - Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé
3 Imagerie Tomographique et Radiothérapie
4 Institut Curie [Paris]
5 Centre Léon Bérard [Lyon]

Purpose: The dose deposited outside of the treatment field during external photon beam radiation therapy treatment, also known as out-of-field dose, is the subject of extensive study as it may be associated with a higher risk of developing a second cancer and could have deleterious effects on the immune system that compromise the efficiency of combined radio-immunotherapy treatments. Out-of-field dose estimation tools developed today in research, including Monte Carlo simulations and analytical methods, are not suited to the requirements of clinical implementation because of their lack of versatility and their cumbersome application. We propose a proof of concept based on deep learning for out-of-field dose map estimation that addresses these limitations. Methods and Materials: For this purpose, a 3D U-Net, considering as inputs the in-field dose, as computed by the treatment planning system, and the patient's anatomy, was trained to predict out-of-field dose maps. The cohort used for learning and performance evaluation included 3151 pediatric patients from the FCCSS database, treated in 5 clinical centers, whose wholebody dose maps were previously estimated with an empirical analytical method. The test set, composed of 433 patients, was split into 5 subdata sets, each containing patients treated with devices unseen during the training phase. Root mean square deviation evaluated only on nonzero voxels located in the out-of-field areas was computed as performance metric. Results: Root mean square deviations of 0.28 and 0.41 cGy/Gy were obtained for the training and validation data sets, respectively. Values of 0.27, 0.26, 0.28, 0.30, and 0.45 cGy/Gy were achieved for the 6 MV linear accelerator, 16 MV linear accelerator, Alcyon cobalt irradiator, Mobiletron cobalt irradiator, and betatron device test sets, respectively.

Domaines: Physique Médicale [physics.med-ph]

Nathan Benzazon, Alexandre Carré, François de Kermenguy, Stéphane Niyoteka, Pauline Maury, et al.. Deep-Learning for Rapid Estimation of the Out-of-Field Dose in External Beam Photon Radiation Therapy – A Proof of Concept. International Journal of Radiation Oncology, Biology, Physics, 2024, 120 (1), pp.253 - 264. ⟨10.1016/j.ijrobp.2024.03.007⟩. ⟨hal-04746121⟩