Applications of DECT in clinical practice are based on two capabilities: material differentiation and material identification and quantification. The capability of obtaining different material-specific datasets (iodine map, virtual unenhanced, and monochromatic images) in the same acquisition can improve lesion detection and characterization. This approach can also affect evaluation of the response to therapy and detection of oncology-related disorders. DECT is an innovative imaging technique that can dramatically affect the care of oncologic patients.

Coronavirus disease 2019 (COVID-19) has become a rapid worldwide pandemic. While COVID-19 primarily manifests as an interstitial pneumonia and severe acute respiratory distress syndrome, severe involvement of other organs has been documented. In this article, we will review the role of non-contrast chest computed tomography in the diagnosis, follow-up and prognosis of patients affected by COVID-19 pneumonia with a detailed description of the imaging findings that may be encountered. Given that patients with COVID-19 may also suffer from coagulopathy, we will discuss the role of CT pulmonary angiography in the detection of acute pulmonary embolism. Finally, we will describe more advanced applications of CT in the differential diagnosis of myocardial injury with an emphasis on ruling out acute coronary syndrome and myocarditis.

Object: The aim of this paper is to investigate the use of fully-convolutional neural networks (FCNNs) to segment scar tissue in the left ventricle from cardiac magnetic resonance with late gadolinium enhancement (CMR-LGE) images. Methods: A successful FCNN in the literature (the ENet) was modified and trained to provide scar-tissue segmentation. Two segmentation protocols (Protocol 1 and Protocol 2) were investigated, the latter limiting the scar-segmentation search area to the left ventricular myocardial tissue region. CMR-LGE from 30 patients with ischemicheart disease were retrospectively analyzed, for a total of 250 images, presenting high variability in terms of scar dimension and location. Segmentation results were assessed against manual scar-tissue tracing using one-patient-out cross validation. Results: Protocol 2 outperformed Protocol 1 significantly (p-value < 0.05), with median sensitivity and Dice similarity coefficient equal to 88.07% (inter-quartile range (IQR) = 18.84%) and 71.25% (IQR = 31.82%), respectively. Discussion: Both segmentation protocols were able to detect scar tissues in the CMR-LGE images but higher performance was achieved when limiting the search area to the myocardial region. The findings of this paper represent an encouraging starting point for the use of FCNNs for the automatic segmentation of nonviable scar tissue from CMR-LGE images.

No abstract

No abstract