European radiology
-
To develop a proof-of-concept "interpretable" deep learning prototype that justifies aspects of its predictions from a pre-trained hepatic lesion classifier. ⋯ • An interpretable deep learning system prototype can explain aspects of its decision-making by identifying relevant imaging features and showing where these features are found on an image, facilitating clinical translation. • By providing feedback on the importance of various radiological features in performing differential diagnosis, interpretable deep learning systems have the potential to interface with standardized reporting systems such as LI-RADS, validating ancillary features and improving clinical practicality. • An interpretable deep learning system could potentially add quantitative data to radiologic reports and serve radiologists with evidence-based decision support.
-
To investigate the diagnostic value of clivopalate angle (CPA) for basilar invagination (BI) at magnetic resonance imaging (MRI). ⋯ • Clivopalate angle has a high diagnostic value for basilar invagination. • Clivopalate angle demonstrates high inter-reader agreement than does clivoaxial angle or clivodens angle. • Clivopalate angle provides complementary information to clivoaxial angle and clivodens angle.
-
In patients with acute ischemic stroke, we aimed to investigate whether microvascular changes, as indexed by capillary transit time heterogeneity (CTH), contribute to the decline of the chance for favorable outcome over time and whether they are a predictor of an intracranial hemorrhage (ICH). ⋯ • The classification of potentially salvageable tissue and infarct core based on traditional net perfusion parameters (as Tmax or CBF) does not account for the microvascular distribution of blood. • However, the microvascular distribution of blood, as indexed by the capillary transit time heterogeneity (CTH), directly affects the availability of oxygen within the hypoperfused tissue and should therefore be respected in acute ischemic stroke imaging. • In our study, mildly elevated CTH is found to be a positive predictor for a favorable clinical outcome and a negative predictor for the occurrence of an intracranial hemorrhage in patients with acute ischemic stroke and homogenous mismatch who underwent ET.