Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffers from poor generalization ability in the presence of dataset shifts. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black box model (Random Forest), both studied with the aim of supporting clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.

This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (<1%), and positive PD-L1 expression (≥1%). Conventional MRI and IVIM-DWI sequences were acquired with a 1.5-T system. Both fixed-size ROIs and freehand segmentations of the tumors were evaluated, and the data were analyzed through a software using four different algorithms. The diffusion (D), pseudodiffusion (D*), and perfusion fraction (pf) were obtained. The correlation between IVIM parameters and PD-L1 expression was studied with Pearson correlation coefficient. The Wilcoxon–Mann–Whitney test was used to study IVIM parameter distributions in the two groups. Twelve patients (57%) had PD-L1 ≥1%, and 9 (43%) <1%. There was a statistically significant correlation between D* values and PD-L1 expression in images analyzed with algorithm 0, for fixed-size ROIs (189.2 ± 65.709 µm²/s × 10⁴ in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 10⁴ in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC.

Background: Benign nerve sheath tumors presenting as solitary retroperitoneal masses (RBNSTs) pose a complex diagnostic challenge for multidisciplinary teams regarding differential diagnosis, staging, and treatment planning. This article reviews the role played by different imaging techniques in assessing RBNSTs and elucidates their typical pathological features with a particular emphasis on the correlation between imaging and histological findings. Furthermore, some examples of retroperitoneal tumors that merit consideration in the process of differential diagnosis based on cross-sectional investigations (CSIs) are reported. The correlation between tissue architecture and appearance on imaging can help increase the accuracy of differential diagnosis with other retroperitoneal neoplasms at CSIs. Critical relevance statement: This educational review critically examines the correlation between imaging and histological features in solitary retroperitoneal benign nerve sheath tumors, offering valuable insights for improving the accuracy of differential diagnosis in clinical radiology. Key Points: RBNSTs are challenging to diagnose because they lack specific radiological features. Differential diagnosis of RBNSTs from other retroperitoneal neoplasms on imaging is complex. Surgical removal of RBNSTs is recommended for an accurate diagnosis. Graphical

Pulmonary hypertension (PH) is a pathophysiological disorder, defined by a mean pulmonary arterial pressure (mPAP) > 20 mmHg at rest, as assessed by right heart catheterization (RHC). PH is not a specific disease, as it may be observed in multiple clinical conditions and may complicate a variety of thoracic diseases. Conditions associated with the risk of developing PH are categorized into five different groups, according to similar clinical presentations, pathological findings, hemodynamic characteristics, and treatment strategy. Most chronic lung diseases that may be complicated by PH belong to group 3 (interstitial lung diseases, chronic obstructive pulmonary disease, combined pulmonary fibrosis, and emphysema) and are associated with the lowest overall survival among all groups. However, some of the chronic pulmonary diseases may develop PH with unclear/multifactorial mechanisms and are included in group 5 PH (sarcoidosis, pulmonary Langerhans’ cell histiocytosis, and neurofibromatosis type 1). This paper focuses on PH associated with chronic lung diseases, in which radiological imaging—particularly computed tomography (CT)—plays a crucial role in diagnosis and classification. Radiologists should become familiar with the hemodynamical, physiological, and radiological aspects of PH and chronic lung diseases in patients at risk of developing PH, whose prognosis and treatment depend on the underlying disease.

Testicular arteries usually arise from the abdominal aorta. During an elective embolization of superior rectal arteries for hemorrhoidal disease performed in a 52-year-old male patient, a previously unreported vascular variant was identified. On selective angiography, the inferior mesenteric artery split into left colic artery and left testicular artery, without any evidence of vascular supply to the hemorrhoidal cushions. Superior rectal arteries were embolized after catheterization of the median sacral artery. A thorough knowledge of vascular variations is essential for interventional radiologists in order to recognize them and avoid potential complications.

Background: Hemostatic abnormalities have been described in COVID-19, and pulmonary microthrombosis was consistently found at autopsy with concomitant severe lung damage. Methods: This is a retrospective observational cross-sectional study including consecutive patients with COVID-19 pneumonia who underwent unenhanced chest CT upon admittance at the emergency room (ER) in one large academic hospital. QCT was used for the calculation of compromised lung volume (%CL). Clinical data were retrieved from patients’ files. Laboratory data were obtained upon presentation at the ER. Aim: The aim of this study was to evaluate the correlation between hemostatic abnormalities and lung involvement in patients affected by COVID-19 pneumonia as described using computer-aided quantitative evaluation of chest CT (quantitative CT (QCT)). Results: A total of 510 consecutive patients (68% males), aged 67 years in median, diagnosed with COVID-19 pneumonia, who underwent unenhanced CT scan upon admission to the ER, were included. In all, 115 patients had %CL > 23%; compared to those with %CL < 23%, they showed higher levels of D-dimer, fibrinogen, and CRP, greater platelet count, and longer PT ratio. Via multivariate regression analysis, BMI ≥ 30 kg/m², D-dimer levels > 500 ng/mL, CRP > 5.0 ng/mL and PT ratio > 1.2 were found to be independent predictors of a %CL > 23% (adjusted odds ratios (95% confidence intervals): 2.1 (1.1–4.0), 3.1 (1.6–5.8), 2.4 (1.3–4.5), and 3.4 (1.4–8.5), respectively). Conclusions: Hemostatic abnormalities in patients affected by COVID-19 correlate with the severity of lung injury as measured by %CL. Our results underline the pathogenetic role of hemostasis in COVID-19 pneumonia beyond the presence of clinically evident thromboembolic complications.