Proper understanding of the risk of radiation-induced late effects for patients receiving external photon beam radiotherapy requires the determination of reliable dose–response relationships. Although significant efforts have been devoted to improving dose estimates for the study of late effects, the most often questioned explanatory variable is still the dose. In this work, based on a literature review, we provide an in-depth description of the radiotherapy dose reconstruction process for the study of late effects. In particular, we focus on the identification of the main sources of dose uncertainty involved in this process and summarise their impacts on the dose–response relationship for radiotherapy late effects. We provide a number of recommendations for making progress in estimating the uncertainties in current studies of radiotherapy late effects and reducing these uncertainties in future studies.

The aim of this study was to determine the effect of reducing the number of image guidance sessions and patient-specific target margins on the dose distribution in the treatment of prostate cancer with helical tomotherapy. 20 patients with prostate cancer who were treated with helical tomotherapy using daily megavoltage CT (MVCT) imaging before treatment served as the study population. The average geometric shifts applied for set-up corrections, as a result of co-registration of MVCT and planning kilovoltage CT studies over an increasing number of image guidance sessions, were determined. Simulation of the consequences of various imaging scenarios on the dose distribution was performed for two patients with different patterns of interfraction changes in anatomy. Our analysis of the daily set-up correction shifts for 20 prostate cancer patients suggests that the use of four fractions would result in a population average shift that was within 1 mm of the average obtained from the data accumulated over all daily MVCT sessions. Simulation of a scenario in which imaging sessions are performed at a reduced frequency and the planning target volume margin is adapted provided significantly better sparing of organs at risk, with acceptable reproducibility of dose delivery to the clinical target volume. Our results indicate that four MVCT sessions on helical tomotherapy are sufficient to provide information for the creation of personalised target margins and the establishment of the new reference position that accounts for the systematic error. This simplified approach reduces overall treatment session time and decreases the imaging dose to the patient.

No abstract

Materials/Methods: We retrospectively pooled a large cohort of patients with head and neck cancer treated with definitive radiation from 2008 to 2018 at a single institution. 59 patients were available for analysis (15 patients with LR). Each patient underwent a planning CT scan, an FDG PET scan, and an attenuation corrected (AC) diagnostic CT scan prior to radiotherapy. The gross tumor volume (GTV) was manually drawn on the planning CT. The AC CT scan was diffeomorphically warped to the planning CT using Advanced Normalization Tools (ANTs: http://stnava. github.io/ANTs/), and the transform was applied to the FDG PET scan. 6321 radiomic features (2077 from each of the three scans) from within the GTV mask were extracted using Pyradiomics package. The extracted radiomics features included first order spatial statistics, shape-based volumetrics, and gray level matrix operations on the original image as well as derived images using a variety of spatial filters. Dimensionality reduction was performed using a logistic regression model, reducing the feature dimensions from 6321 to 2754. The remaining features were then fed into a variety of machine learning models to train (N Z 35) and validate (N Z 24) the predictive model with a balanced number of recurrences in the training and validation sets. The model performance was evaluated using receiver operating characteristic (ROC) curve. We further identified the most important features that may affect prognosis. Results: The machine learning models were able to significantly predict locoregional recurrence in our cohort of 59 patients. The classifier performance of the random forests model revealed an area under the curve (AUC) of 0.81 +/-0.13. The top feature weights used a combination of features from all three scans, indicating the need for the multi-modal approach of all three scans. Conclusion: We built machine learning models that can be used to predict locoregional recurrence in patients underwent head and neck radiation using pre-treatment PET and CT scans. This model can be applied to better stratify patients based on pre-treatment images towards personalized treatment. We used automated advanced non-linear registrations and neural networks to improve performance from prior models. The approach can be tailored to optimize medical management using data-driven models.

No abstract