RESUMEN
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 distribution, 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-1, 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 distributions suggests a viable alternative to 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.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Transferencia Lineal de Energía , Método de Montecarlo , Terapia de Protones , Terapia de Protones/métodos , Humanos , Neoplasias Encefálicas/radioterapia , Neoplasias Encefálicas/diagnóstico por imagen , Planificación de la Radioterapia Asistida por Computador/métodos , Dosificación RadioterapéuticaRESUMEN
To examine the comparative robustness of computed tomography (CT)-based conventional radiomics and deep-learning convolutional neural networks (CNN) to predict overall survival (OS) in HCC patients. Retrospectively, 114 HCC patients with pretherapeutic CT of the liver were randomized into a development (n = 85) and a validation (n = 29) cohort, including patients of all tumor stages and several applied therapies. In addition to clinical parameters, image annotations of the liver parenchyma and of tumor findings on CT were available. Cox-regression based on radiomics features and CNN models were established and combined with clinical parameters to predict OS. Model performance was assessed using the concordance index (C-index). Log-rank tests were used to test model-based patient stratification into high/low-risk groups. The clinical Cox-regression model achieved the best validation performance for OS (C-index [95% confidence interval (CI)] 0.74 [0.57-0.86]) with a significant difference between the risk groups (p = 0.03). In image analysis, the CNN models (lowest C-index [CI] 0.63 [0.39-0.83]; highest C-index [CI] 0.71 [0.49-0.88]) were superior to the corresponding radiomics models (lowest C-index [CI] 0.51 [0.30-0.73]; highest C-index [CI] 0.66 [0.48-0.79]). A significant risk stratification was not possible (p > 0.05). Under clinical conditions, CNN-algorithms demonstrate superior prognostic potential to predict OS in HCC patients compared to conventional radiomics approaches and could therefore provide important information in the clinical setting, especially when clinical data is limited.
Asunto(s)
Carcinoma Hepatocelular , Aprendizaje Profundo , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/diagnóstico por imagen , Radiómica , Estudios Retrospectivos , Neoplasias Hepáticas/diagnóstico por imagen , AlgoritmosRESUMEN
PURPOSE/OBJECTIVE: Experimental in vivo determination of radiological tissue parameters of organs in the head and pelvis within a large patient cohort, expanding on the current standard human tissue database summarized in ICRU46. MATERIAL/METHODS: Relative electron density (RED), effective atomic number (EAN) and stopping-power ratio (SPR) were obtained from clinical dual-energy CT scans using a clinically validated DirectSPR implementation and organ segmentations of 107 brain-tumor (brain, brainstem, spinal cord, chiasm, optical nerve, lens) and 120 pelvic cancer patients (prostate, kidney, liver, bladder). The impact of contamination by surrounding tissues on the tissue parameters was reduced with a dedicated contour adaption routine. Tissue parameters were characterized regarding the cohort mean value as well as the variation within each patient (2σintra) and between patients (2σinter). For the brain, age-dependent differences were determined. RESULTS: For 10 organs, including 4 structures not listed in ICRU46, the mean RED, EAN and SPR as well as their respective intra- and inter-patient variation were determined. SPR intra-patient variation was higher than 1.3% (1.3-4.6%) in all organs and always exceeded the inter-patient variation of the organ mean SPR (0.6-2.1%). For the brain, a significant SPR variation between pediatric and non-pediatric patients was determined. CONCLUSION: Radiological tissue parameters in the head and pelvis were characterized in vivo for a large patient cohort using dual-energy CT. This reassesses parts of the current standard database defined in ICRU46, furthermore complementing the data described in literature by smaller substructures in the brain as well as by the quantification of organ-specific inter- and intra-patient variation.