Radiomics is defined as the use of automated or semi-automated post-processing and analysis of multiple features derived from imaging exams. Extracted features might generate models able to predict the molecular profile of solid tumors. The aim of this study was to develop a predictive algorithm to define the mutational status of EGFR in treatment-naïve patients with advanced non–small cell lung cancer (NSCLC). CT scans from 109 treatment-naïve patients with NSCLC (21 EGFR-mutant and 88 EGFR-wild type) underwent radiomics analysis to develop a machine learning model able to recognize EGFR-mutant from EGFR-WT patients via CT scans. A “test–retest” approach was used to identify stable radiomics features. The accuracy of the model was tested on an external validation set from another institution and on a dataset from the Cancer Imaging Archive (TCIA). The machine learning model that considered both radiomic and clinical features (gender and smoking status) reached a diagnostic accuracy of 88.1% in our dataset with an AUC at the ROC curve of 0.85, whereas the accuracy values in the datasets from TCIA and the external institution were 76.6% and 83.3%, respectively. Furthermore, 17 distinct radiomics features detected at baseline CT scan were associated with subsequent development of T790M during treatment with an EGFR inhibitor. In conclusion, our machine learning model was able to identify EGFR-mutant patients in multiple validation sets with globally good accuracy, especially after data optimization. More comprehensive training sets might result in further improvement of radiomics-based algorithms. Significance: These findings demonstrate that data normalization and “test–retest” methods might improve the performance of machine learning models on radiomics images and increase their reliability when used on external validation datasets.

Data on the pathology of COVID-19 are scarce; available studies show diffuse alveolar damage; however, there is scarce information on the chronologic evolution of COVID-19 lung lesions. The primary aim of the study is to describe the chronology of lung pathologic changes in COVID-19 by using a post-mortem transbronchial lung cryobiopsy approach. Our secondary aim is to correlate the histologic findings with computed tomography patterns. SARS-CoV-2-positive patients, who died while intubated and mechanically ventilated, were enrolled. The procedure was performed 30 min after death, and all lung lobes sampled. Histopathologic analysis was performed on thirty-nine adequate samples from eight patients: two patients (illness duration < 14 days) showed early/exudative phase diffuse alveolar damage, while the remaining 6 patients (median illness duration—32 days) showed progressive histologic patterns (3 with mid/proliferative phase; 3 with late/fibrotic phase diffuse alveolar damage, one of which with honeycombing). Immunohistochemistry for SARS-CoV-2 nucleocapsid protein was positive predominantly in early-phase lesions. Histologic patterns and tomography categories were correlated: early/exudative phase was associated with ground-glass opacity, mid/proliferative lesions with crazy paving, while late/fibrous phase correlated with the consolidation pattern, more frequently seen in the lower/middle lobes. This study uses an innovative cryobiopsy approach for the post-mortem sampling of lung tissues from COVID-19 patients demonstrating the progression of fibrosis in time and correlation with computed tomography features. These findings may prove to be useful in the correct staging of disease, and this could have implications for treatment and patient follow-up.

Delta-radiomics is a branch of radiomics in which features are confronted after time or after introducing an external factor (such as treatment with chemotherapy or radiotherapy) to extrapolate prognostic data or to monitor a certain condition. Immune checkpoint inhibitors (ICIs) are currently revolutionizing the treatment of non-small cell lung cancer (NSCLC); however, there are still many issues in defining the response to therapy. Contrast-enhanced CT scans of 33 NSCLC patients treated with ICIs were analyzed; altogether, 43 lung lesions were considered. The radiomic features of the lung lesions were extracted from CT scans at baseline and at first reassessment, and their variation (delta, Δ) was calculated by means of the absolute difference and relative reduction. This variation was related to the final response of each lesion to evaluate the predictive ability of the variation itself. Twenty-seven delta features have been identified that are able to discriminate radiologic response to ICIs with statistically significant accuracy. Furthermore, the variation of nine features significantly correlates with pseudo-progression.

An emerging clinical need is represented by identifying reliable biomarkers able to discriminate between responders and non-responders among patients showing imaging progression during the administration of immune checkpoints inhibitors for advanced non-small cell lung cancer (NSCLC). In the present study, we analyzed the prognostic power of peripheral-blood systemic inflammation indexes and 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) in this clinical setting. In 45 patients showing radiological progression (defined as RECIST 1.1 progressive disease) during Nivolumab administration, the following lab and imaging parameters were collected: neutrophil-to-lymphocyte ratio (NLR), derived-NLR (dNLR), lymphocyte-to-monocyte ratio (LMR), platelets-to-lymphocyte ratio (PLR), systemic inflammation index (SII), maximum standardized uptake value, metabolic tumor volume (MTV), and total lesion glycolysis (TLG). MTV and SII independently predicted OS. Their combination in the immune metabolic prognostic index (IMPI) allowed the identification of patients who might benefit from immunotherapy continuation, despite radiological progression. The combination of FDG PET/CT volumetric data with SII also approximates the immune-metabolic response with respect to baseline, providing additional independent prognostic insights. In conclusion, the degree of systemic inflammation, the quantification of the metabolically active tumor burden, and their combination might disclose the radiological progression in NSCLC patients receiving Nivolumab.

The eighth edition of the TNM classification officially introduced “depth of invasion” (DOI) as a criterion for determining the T stage in tongue squamous cell carcinoma. The DOI is a well-known independent risk factor for nodal metastases. In fact, several experts strongly suggest elective neck dissection for tongue cancer with a DOI > 4 mm due to the high risk of early and occult nodal metastases. Imaging plays a pivotal role in preoperative assessments of the DOI and, hence, in planning the surgical approach. Intraoral ultrasound (IOUS) has been proposed for early-stage SCC of the oral tongue as an alternative to magnetic resonance imaging (MRI) for local staging. The aim of this work is to investigate the accuracy of IOUS in the assessment of the DOI in early oral SCC (CIS, pT1, and pT2). A total of 41 patients with tongue SCCs (CIS-T2) underwent a preoperative high-frequency IOUS. An IOUS was performed using a small-size, high-frequency hockey-stick linear probe. The ultrasonographic DOI (usDOI) was retrospectively compared to the pathological DOI (pDOI) as the standard reference. In patients who underwent a preoperative MRI, their usDOI, magnetic resonance DOI (mriDOI), and pDOI were compared. Specificity and sensitivity for the IOUS to predict a pDOI > 4 mm and to differentiate invasive and noninvasive tumors were also evaluated. A high correlation was found between the pDOI and usDOI, pDOI and mriDOI, and usDOI and mriDOI (Spearman’s ρ = 0.84, p < 0.0001, Spearman’s ρ = 0.79, p < 0.0001, and Spearman’s ρ = 0.91, p < 0.0001, respectively). A Bland–Altman plot showed a high agreement between the usDOI and pDOI, even though a mean systematic error was found between the usDOI and pDOI (0.7 mm), mriDOI and pDOI (1.6 mm), and usDOI and mriDOI (−0.7 mm). The IOUS was accurate at determining the T stage (p < 0.0001). The sensitivity and specificity for the IOUS to predict a pDOI ≥4 mm were 92.31% and 82.14%, respectively, with an AUC of 0.87 (p < 0.0001). The specificity, sensitivity, negative predictive value (NPV), and positive predictive value (PPV) for the IOUS to predict an invasive cancer were 100%, 94.7%, 60%, and 100%, respectively. The AUC was 0.8 (95% CI 0.646–0.908, p < 0.0001). The IOUS was accurate in a preoperative assessment of a pDOI and T stage, and can be proposed as an alternative to MRI in the preoperative staging of tongue SCC.

Introduction: Systemic sclerosis (SSc) is a systemic immune-mediated disease, featuring fibrosis of the skin and organs, and has the greatest mortality among rheumatic diseases. The nervous system involvement has recently been demonstrated, although actual lung involvement is considered the leading cause of death in SSc and, therefore, should be diagnosed early. Pulmonary function tests are not sensitive enough to be used for screening purposes, thus they should be flanked by other clinical examinations; however, this would lead to a risk of overtesting, with considerable costs for the health system and an unnecessary burden for the patients. To this extent, Machine Learning (ML) algorithms could represent a useful add-on to the current clinical practice for diagnostic purposes and could help retrieve the most useful exams to be carried out for diagnostic purposes. Method: Here, we retrospectively collected high resolution computed tomography, pulmonary function tests, esophageal pH impedance tests, esophageal manometry and reflux disease questionnaires of 38 patients with SSc, applying, with R, different supervised ML algorithms, including lasso, ridge, elastic net, classification and regression trees (CART) and random forest to estimate the most important predictors for pulmonary involvement from such data. Results: In terms of performance, the random forest algorithm outperformed the other classifiers, with an estimated root-mean-square error (RMSE) of 0.810. However, this algorithm was seen to be computationally intensive, leaving room for the usefulness of other classifiers when a shorter response time is needed. Conclusions: Despite the notably small sample size, that could have prevented obtaining fully reliable data, the powerful tools available for ML can be useful for predicting early lung involvement in SSc patients. The use of predictors coming from spirometry and pH impedentiometry together might perform optimally for predicting early lung involvement in SSc.