The current focus on networking and mutual assistance in the management of radiation accidents or incidents has demonstrated the importance of a joined-up approach in physical and biological dosimetry. To this end, the European Radiation Dosimetry Working Group 10 on ‘Retrospective Dosimetry’ has been set up by individuals from a wide range of disciplines across Europe. Here, established and emerging dosimetry methods are reviewed, which can be used immediately and retrospectively following external ionising radiation exposure. Endpoints and assays include dicentrics, translocations, premature chromosome condensation, micronuclei, somatic mutations, gene expression, electron paramagnetic resonance, thermoluminescence, optically stimulated luminescence, neutron activation, haematology, protein biomarkers and analytical dose reconstruction. Individual characteristics of these techniques, their limitations and potential for further development are reviewed, and their usefulness in specific exposure scenarios is discussed. Whilst no single technique fulfils the criteria of an ideal dosemeter, an integrated approach using multiple techniques tailored to the exposure scenario can cover most requirements.

Predictive models based on radiomics and machine-learning (ML) need large and annotated datasets for training, often difficult to collect. We designed an operative pipeline for model training to exploit data already available to the scientific community. The aim of this work was to explore the capability of radiomic features in predicting tumor histology and stage in patients with non-small cell lung cancer (NSCLC). We analyzed the radiotherapy planning thoracic CT scans of a proprietary sample of 47 subjects (L-RT) and integrated this dataset with a publicly available set of 130 patients from the MAASTRO NSCLC collection (Lung1). We implemented intra- and inter-sample cross-validation strategies (CV) for evaluating the ML predictive model performances with not so large datasets. We carried out two classification tasks: histology classification (3 classes) and overall stage classification (two classes: stage I and II). In the first task, the best performance was obtained by a Random Forest classifier, once the analysis has been restricted to stage I and II tumors of the Lung1 and L-RT merged dataset (AUC = 0.72 ± 0.11). For the overall stage classification, the best results were obtained when training on Lung1 and testing of L-RT dataset (AUC = 0.72 ± 0.04 for Random Forest and AUC = 0.84 ± 0.03 for linear-kernel Support Vector Machine). According to the classification task to be accomplished and to the heterogeneity of the available dataset(s), different CV strategies have to be explored and compared to make a robust assessment of the potential of a predictive model based on radiomics and ML.