Search

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., (Copyright © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.)

It is established that human movements in the vicinity of a permanent static magnetic field, such as those in magnetic resonance imaging (MRI) scanners induce electric fields in the human body; this raises potential severe risks of health to radiographers and cleaners exposed routinely to these fields in MRI rooms. The relevant directives and parameters, however, are based on theoretical models, and accurate studies on the simulation of the effects based on human movement data obtained in real conditions are still lacking. Two radiographers and one cleaner, familiar with MRI room activities and these directives, were gait analyzed during the execution of routine job motor tasks at different velocities. Full body motion was recorded in a gait laboratory arranged to reproduce the workspace of a room with an MRI full-body scanner. Body segments were tracked with clusters of at least three markers, from which position and velocity of the centroids were calculated. These were used as input in an established computer physical model able to map the stray field in an MRI room. The spatial peak values of the calculated electric field induced by motion of the head and of the entire body during these tasks, for both the health and sensory effects, were found smaller than the thresholds recommended by the European directives, for both 1.5 T and 3.0 T MRI. These tasks therefore seem to guarantee the safety of MRI room operators according to current professional good practice for exposure risks. Physical modeling and experimental measures of human motion can also support occupational medicine., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Gurrera, Leardini, Ortolani, Durante, Caputo, Gallias, Abbate, Rinaldi, Iacoviello, Acri, Vermiglio and Marrale.)

Does the exposure of magnetic resonance imaging personnel to static magnetic fields fully comply with Directive 2013/35/EU? Despite the obligation to satisfy this question, a general answer cannot be provided, nor are final satisfying good practices methods for exposure assessment currently available. In order to contribute to fix this problem, three different 1.5 T scanners are analysed and - by a new theoretical insight - a positive answer is provided., (Copyright © 2018 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.)