Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

Drug-eluting bead transarterial chemoembolization (DEB-TACE) is a relative new endovascular treatment based on the use of microspheres to release chemotherapeutic agents within a target lesion with controlled pharmacokinetics. This aspect justifies the immediate success of DEB-TACE, that nowadays represents one of the most used treatments for unresectable hepatocellular carcinoma. However, there is no consensus about the choice of the best embolotherapy technique. In this review, we describe the available microspheres and report the results of the main comparative studies, to clarify the role of DEB-TACE in the hepatocellular carcinoma management. We underline that there is no evidence about the superiority of DEB-TACE over conventional TACE in terms of efficacy, but there may be some benefits with respect to safety especially with the improvement of new technologies.

MRI is a useful diagnostic tool in the preoperative evaluation of MRKH syndrome and is less expensive and invasive than laparoscopy. Strong cooperation between radiologists and surgeons is highly recommended.

The aim of this study was to compare the Intravoxel Incoherent Motion (IVIM) parameters between healthy Peripheral Zone (PZ), Benign Prostatic Hyperplasia (BPH) and Prostate Cancer (PCa) and compare them to assess whether there was correlation with Gleason Score (GS) grading system. Thirty-one patients with suspect of PCa underwent 1.5T Multi-Parametric Magnetic Resonance Imaging (MP-MRI) with endorectal coil with a protocol including T2WI, DWI using 10 b values (0, 10, 20, 30, 50, 80, 100, 200, 400, 1000 s/mm) and DCE. Monoexponential and IVIM model fits were used to calculate both apparent diffusion coefficient (ADC) and the following IVIM parameters: molecular diffusion coefficient (D), perfusion-related diffusion coefficient (D*) and perfusion fraction (f). The ADC and D values were significantly lower in the PCa (0.70 ± 0.16 × 10 mm/s and 0.88 ± 0.31 × 10 mm/s) compared to those found in the PZ (1.22 ± 0.20 × 10 mm/s and 1.78 ± 0.34 × 10 mm/s) and in the BPH (1.53 ± 0.23 × 10 mm/s and 1.11 ± 0.28 × 10 mm/s). The D* parameter was significantly increased in the PCa (5.35 ± 5.12 × 10 mm/s) compare to the healthy PZ (3.02 ± 2.86 × 10 mm/s), instead there was not significantly difference in the PCa compare to the BPH (5.61 ± 6.77 × 10 mm/s). The f was statistically lower in the PCa (9.01 ± 5.20%) compared to PZ (10.57 ± 9.30%), but not significantly different between PCa and BPH (9.29 ± 7.29%). The specificity, sensitivity and accuracy of T2WI associated with DWI and IVIM were higher (100, 98 and 99%, respectively) than for T2WI/DWI and IVIM alone (89, 92 and 90%, respectively). Only for ADC was found a statistical difference between low- and intermediate-/high-grade tumors. Adding IVIM to the MP-MRI could increase the diagnostic performance to detect clinically relevant PCa. ADC values have been found to have a rule to discriminate PCa reliably from normal areas and differed significantly in low- and intermediate-/high-grade PCa. In contrast, IVIM parameters were unable to distinguish between the different GS.