A deep-learning-based surrogate model for Monte-Carlo simulations of the linear energy transfer in primary brain tumor patients treated with proton-beam radiotherapy.

OBJECTIVE: This study explores the use of neural networks (NNs) as surrogate models for Monte-Carlo (MC) simulations in predicting the dose-averaged linear energy transfer (LETd) of protons in proton-beam therapy based on the planned dose distribution and patient anatomy in the form of computed tomography (CT) images. As LETdis associated with variability in the relative biological effectiveness (RBE) of protons, we also evaluate the implications of using NN predictions for normal tissue complication probability (NTCP) models within a variable-RBE context. Approach: The predictive performance of three-dimensional NN architectures was evaluated using five-fold cross-validation on a cohort of brain tumor patients (n=151). The best-performing model was identified and externally validated on patients from a different center (n=107). LETdpredictions were compared to MC-simulated results in clinically relevant regions of interest. We assessed the impact on NTCP models by leveraging LETdpredictions to derive RBE-weighted doses, using the Wedenberg RBE model. Main results: We found NNs based solely on the planned dose profile, i.e. without additional usage of CT images, can approximate MC-based LETddistributions. Root mean squared errors (RMSE) for the median LETdwithin the brain, brainstem, CTV, chiasm, lacrimal glands (ipsilateral/contralateral) and optic nerves (ipsilateral/contralateral) were 0.36, 0.87, 0.31, 0.73, 0.68, 1.04, 0.69 and 1.24~keV/µm, respectively. Although model predictions showed statistically significant differences from MC outputs, these did not result in substantial changes in NTCP predictions, with RMSEs of at most 3.2 percentage points. Significance: The ability of NNs to predict LETdbased solely on planned dose profiles suggests a viable alternative to the compute-intensive MC simulations in a variable-RBE setting. This is particularly useful in scenarios where MC simulation data are unavailable, facilitating resource-constrained proton therapy treatment planning, retrospective patient data analysis and further investigations on the variability of proton RBE.

Endothelial Cell Response to Combined Photon or Proton Irradiation with Doxorubicin.

Surgery, radiotherapy, and chemotherapy are essential treatment modalities to target cancer cells, but they frequently cause damage to the normal tissue, potentially leading to side effects. As proton beam radiotherapy (PBT) can precisely spare normal tissue, this therapeutic option is of increasing importance regarding (neo-)adjuvant and definitive anti-cancer therapies. Akin to photon-based radiotherapy, PBT is often combined with systemic treatment, such as doxorubicin (Dox). This study compares the cellular response of human microvascular endothelial cells (HMEC-1) following irradiation with photons (X) or protons (H) alone and also in combination with different sequences of Dox. The cellular survival, cell cycle, apoptosis, proliferation, viability, morphology, and migration were all investigated. Dox monotreatment had minor effects on all endpoints. Both radiation qualities alone and in combination with longer Dox schedules significantly reduced clonogenic survival and proliferation, increased the apoptotic cell fraction, induced a longer G2/M cell cycle arrest, and altered the cell morphology towards endothelial-to-mesenchymal-transition (EndoMT) processes. Radiation quality effects were seen for metabolic viability, proliferation, and motility of HMEC-1 cells. Additive effects were found for longer Dox schedules. Overall, similar effects were found for H/H-Dox and X/X-Dox. Significant alterations between the radiation qualities indicate different but not worse endothelial cell damage by H/H-Dox.

Efficacy and Feasibility of Proton Beam Therapy in Relapsed High-Risk Neuroblastoma-Experiences from the Prospective KiProReg Registry.

BACKGROUND: Despite an intensive multimodal treatment approach, approximately 50% of high-risk (HR) neuroblastoma (NB) patients experience progression. Despite the advances in targeted therapy, high-dose chemotherapy, and other systemic treatment options, radiation therapy (RT) to sites of relapsed disease can be an option to reduce tumor burden and improve chance for disease control. METHODS: Patients who received salvage irradiation with proton beam therapy (PBT) for local or metastatic relapse of HR NB within the prospective registry trials KiProReg and ProReg were eligible for this retrospective analysis. Data on patient characteristics, multimodality therapy, adverse events, and oncologic endpoints were evaluated. Adverse events were assessed before, during, and after PBT according to common terminology criteria for adverse events (CTCAE) V4.0. RESULTS: Between September 2013 and September 2020, twenty (11 male; 9 female) consecutive patients experiencing local (N = 9) or distant recurrence (N = 25) were identified for this analysis. Distant recurrences included osteomedullary (N = 11) or CNS lesions (N = 14). Salvage therapy consisted of re-induction chemo- or chemo-immuno-therapy (N = 19), surgery (N = 6), high-dose chemotherapy and stem cell transplantation (N = 13), radiation (N = 20), and concurrent systemic therapy. Systemic therapy concurrent to RT was given to six patients and included temozolomide (N = 4), carboplatine (N = 1), or anaplastic lymphoma kinase tyrosine kinase inhibitors (ALK-TKI) (N = 1). A median dose of 36 Gy was applied to the 34 recurrent sites. Local RT was applied to 15 patients, while five patients, received craniospinal irradiation for CNS relapse. After a median follow-up (FU) of 20 months (4-66), the estimated rate for local control, distant metastatic free survival, and overall survival at 3 years was 68.0%, 37.9%, and 61.6%, respectively. During RT, ten patients (50%) presented with a higher-grade acute hematologic adverse event. Late higher-grade sequelae included transient myelitis with transverse section (N = 2) and secondary malignancy outside of the RT field (N = 1). CONCLUSION: Our study demonstrates the efficacy and safety of RT/PBT for recurrent HR NB in a multimodality second-line approach. To better define the role of RT for these patients, prospective studies would be desirable.

Evaluation of a New Inverse, Globally Convex Treatment Planning System Algorithm for Gamma Knife Radiation Surgery Within a Prospective Trial: Advantages and Disadvantages in Practical Application.

Purpose: A new inverse planning software called IntuitivePlan (IP) based on a global convex optimization algorithm was adopted for the Gamma Knife radiation surgery. We investigated IP's suitability for daily clinical use and its applicability for different cerebral entities. Methods and Materials: For 230 target volumes, IP was tested in a prospective trial. The computed treatment plans were compared with conventional expert preplans, which included forward planning by the expert and local internal optimization. Based on the same dose constraints, we used the default settings for the inverse calculation of the treatment plans. Plan quality metrics such as the Paddick conformity index were compared for both planning techniques with additional subdivisions into the 3 selectable IP planning strategies and different entity groups. Results: IP calculated treatment plans of quality similar to that of preplans created by expert planners. Some plan quality metrics, especially those related to conformity and dose gradient, attained statistically significantly higher scores combined with high coverage for the inversely generated plans except for the selectivity optimizing strategy. Normal brain volume receiving 10 Gy or 12 Gy or higher (V 1 0 Gy or V 1 2 Gy ) did not show significant differences for the coverage optimizing strategies. The IP software demonstrated significantly shorter planning times versus manual planning as well as greater numbers of isocenters, often associated with longer treatment times. In terms of total time, these differences almost balanced out again. Conclusions: Our results suggest that IP is advantageous for complex tumors. We observed general clinical significance for conformity and superiority for the selectivity optimizing strategy. In addition, the high-quality calculation from IP enables novices in the profession to achieve pre-treatment plans of a quality similar to that of expert planners. IP allows for optimizing the sparing of surrounding tissue and conformity for benign tumors within a short time. Thus, IP forms a solid basis for further planning on the treatment day.