Session Item

Radiation therapy has common iatrogenic effects, including the development of radiation-induced lymphopenia, radiation-induced cancer, and cardiac and vascular complications. A growing body of scientific evidence reveals the potential effects of medium (Gy) and low doses (< 1 Gy) in particular on highly radiosensitive immune cells. Therefore, the assessment of low doses inevitably delivered outside the treatment field (out-of-field dose) is a topic of renewed interest at a pivotal moment in the development of combination therapies. In this work, we propose an original fast and versatile tool to estimate out-of-field doses for patients treated with external photon radiotherapy with energies above 1 MV based on a Deep Learning approach.

3152 pediatric patients from the French Childhood Cancer Survivor Study dataset who underwent 2D conventional and 3D conformational radiotherapies between 1953 and 2013 with accelerators operating with photons at energies higher than 1 MV were considered in this study (Table 1). A 3D U-Net architecture was investigated, considering in-field doses and patient geometries as inputs while using whole-body dose maps estimated with analytical models (Dos-EG) as ground truths. In addition to the traditional test set (test set), data from one specific center (center test set) and one specific linear accelerator (linac test set) were kept unseen during the neural network training. Data were split in 67%, 14%, 14%, 2% and 3% for the train, validation, test, center test and linac test set respectively.

Table 1: Distribution of accelerators and pathologies in the work cohort

Figure 1 shows an example of out-of-field dose prediction, and quantitative Root Mean Square Difference (RMSD) results can be found in Table 2.

Figure 1: Example of predicted out-of-field dose map (with blue square) VS ground truth out-of-field dose map, for a male patient treated on a Co60 accelerator for a nephroblastoma

Table 2: Results at epoch 1975/2000 after a 160h training

The results suggest that the initial hypothesis is validated, i.e. it is possible to estimate the out-of-field dose from the in-field dose map and the anatomy of the patient. The results on the test set, center test set, and linac test set seems to demonstrate good generalization performances, which is promising for large-scale applications on retrospective and prospective datasets and opens the door to a better understanding of dose-response relationships in the context of radiation-induced lymphopenia.

This work has benefited from the grant ANR-21-RHU5-0005 within the FRANCE2030 investment plan.