LymphoDose: a lymphocyte dose estimation framework-application to brain radiotherapy.

Objective. Severe radiation-induced lymphopenia occurs in 40% of patients treated for primary brain tumors and is an independent risk factor of poor survival outcomes. We developed anin-silicoframework that estimates the radiation doses received by lymphocytes during volumetric modulated arc therapy brain irradiation.Approach. We implemented a simulation consisting of two interconnected compartmental models describing the slow recirculation of lymphocytes between lymphoid organs (M1) and the bloodstream (M2). We used dosimetry data from 33 patients treated with chemo-radiation for glioblastoma to compare three cases of the model, corresponding to different physical and biological scenarios: (H1) lymphocytes circulation only in the bloodstream i.e. circulation inM2only; (H2) lymphocytes recirculation between lymphoid organs i.e. circulation inM1andM2interconnected; (H3) lymphocytes recirculation between lymphoid organs and deep-learning computed out-of-field (OOF) dose to head and neck (H&N) lymphoid structures. A sensitivity analysis of the model's parameters was also performed.Main results. For H1, H2 and H3 cases respectively, the irradiated fraction of lymphocytes was 99.8 ± 0.7%, 40.4 ± 10.2% et 97.6 ± 2.5%, and the average dose to irradiated pool was 309.9 ± 74.7 mGy, 52.6 ± 21.1 mGy and 265.6 ± 48.5 mGy. The recirculation process considered in the H2 case implied that irradiated lymphocytes were irradiated in the field only 1.58 ± 0.91 times on average after treatment. The OOF irradiation of H&N lymphoid structures considered in H3 was an important contribution to lymphocytes dose. In all cases, the estimated doses are low compared with lymphocytes radiosensitivity, and other mechanisms could explain high prevalence of RIL in patients with brain tumors.Significance. Our framework is the first to take into account OOF doses and recirculation in lymphocyte dose assessment during brain irradiation. Our results demonstrate the need to clarify the indirect effects of irradiation on lymphopenia, in order to potentiate the combination of radio-immunotherapy or the abscopal effect.

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

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 whole-body 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. CONCLUSIONS: This proof-of-concept approach using a convolutional neural network has demonstrated unprecedented generalizability for this task, although it remains limited, and brings us closer to an implementation compatible with clinical routine.