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.

In particle therapy, the uncertainty of the delivered particle range during the patient irradiation limits the optimization of the treatment planning. Therefore, an in vivo treatment verification device is required, not only to improve the plan robustness, but also to detect significant interfractional morphological changes during the treatment itself. In this article, an effective and robust analysis to detect regions with a significant range discrepancy is proposed. This study relies on an in vivo treatment verification by means of in-beam Positron Emission Tomography (PET) and was carried out with the INSIDE system installed at the National Center of Oncological Hadrontherapy (CNAO) in Pavia, which is under clinical testing since July 2019. Patients affected by head-and-neck tumors treated with protons have been considered. First, in order to tune the analysis parameters, a Monte Carlo (MC) simulation was carried out to reproduce a patient who required a replanning because of significant morphological changes found during the treatment. Then, the developed approach was validated on the experimental measurements of three patients recruited for the INSIDE clinical trial (ClinicalTrials.govID: NCT03662373), showing the capability to estimate the treatment compliance with the prescription both when no morphological changes occurred and when a morphological change did occur, thus proving to be a promising tool for clinicians to detect variations in the patients treatments.

Purpose: This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability and the annotation quality are relevant factors in training AI-methods. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria. Methods: We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The first one (U-net $$_1$$1 ) is devoted to the identification of the lung parenchyma; the second one (U-net $$_2$$2 ) acts on a bounding box enclosing the segmented lungs to identify the areas affected by COVID-19 lesions. Different public datasets were used to train the U-nets and to evaluate their segmentation performances, which have been quantified in terms of the Dice Similarity Coefficients. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated. Results: Both the volumetric DSC (vDSC) and the accuracy showed a dependency on the annotation quality of the released data samples. On an independent dataset (COVID-19-CT-Seg), both the vDSC and the surface DSC (sDSC) were measured between the masks predicted by LungQuant system and the reference ones. The vDSC (sDSC) values of 0.95±0.01 and 0.66±0.13 (0.95±0.02 and 0.76±0.18, with 5 mm tolerance) were obtained for the segmentation of lungs and COVID-19 lesions, respectively. The system achieved an accuracy of 90% in CT-SS identification on this benchmark dataset. Conclusion: We analysed the impact of using data samples with different annotation criteria in training an AI-based quantification system for pulmonary involvement in COVID-19 pneumonia. In terms of vDSC measures, the U-net segmentation strongly depends on the quality of the lesion annotations. Nevertheless, the CT-SS can be accurately predicted on independent test sets, demonstrating the satisfactory generalization ability of the LungQuant.

We propose and evaluate a procedure for the explainability of a breast density deep learning based classifier. A total of 1662 mammography exams labeled according to the BI-RADS categories of breast density was used. We built a residual Convolutional Neural Network, trained it and studied the responses of the model to input changes, such as different distributions of class labels in training and test sets and suitable image pre-processing. The aim was to identify the steps of the analysis with a relevant impact on the classifier performance and on the model explainability. We used the grad-CAM algorithm for CNN to produce saliency maps and computed the Spearman’s rank correlation between input images and saliency maps as a measure of explanation accuracy. We found that pre-processing is critical not only for accuracy, precision and recall of a model but also to have a reasonable explanation of the model itself. Our CNN reaches good performances compared to the state-of-art and it considers the dense pattern to make the classification. Saliency maps strongly correlate with the dense pattern. This work is a starting point towards the implementation of a standard framework to evaluate both CNN performances and the explainability of their predictions in medical image classification problems.

Purpose: In‐beam positron emission tomography (PET) is one of the modalities that can be used for in vivo noninvasive treatment monitoring in proton therapy. Although PET monitoring has been frequently applied for this purpose, there is still no straightforward method to translate the information obtained from the PET images into easy‐to‐interpret information for clinical personnel. The purpose of this work is to propose a statistical method for analyzing in‐beam PET monitoring images that can be used to locate, quantify, and visualize regions with possible morphological changes occurring over the course of treatment.Methods: We selected a patient treated for squamous cell carcinoma (SCC) with proton therapy, to perform multiple Monte Carlo (MC) simulations of the expected PET signal at the start of treatment, and to study how the PET signal may change along the treatment course due to morphological changes. We performed voxel‐wise two‐tailed statistical tests of the simulated PET images, resembling the voxel‐based morphometry (VBM) method commonly used in neuroimaging data analysis, to locate regions with significant morphological changes and to quantify the change.Results: The VBM resembling method has been successfully applied to the simulated in‐beam PET images, despite the fact that such images suffer from image artifacts and limited statistics. Three dimensional probability maps were obtained, that allowed to identify interfractional morphological changes and to visualize them superimposed on the computed tomography (CT) scan. In particular, the characteristic color patterns resulting from the two‐tailed statistical tests lend themselves to trigger alarms in case of morphological changes along the course of treatment.Conclusions: The statistical method presented in this work is a promising method to apply to PET monitoring data to reveal interfractional morphological changes in patients, occurring over the course of treatment. Based on simulated in‐beam PET treatment monitoring images, we showed that with our method it was possible to correctly identify the regions that changed. Moreover we could quantify the changes, and visualize them superimposed on the CT scan. The proposed method can possibly help clinical personnel in the replanning procedure in adaptive proton therapy treatments.