Artificial Intelligence for Cardiothoracic Imaging: Overview of Current and Emerging Applications.

Artificial intelligence algorithms can learn by assimilating information from large datasets in order to decipher complex associations, identify previously undiscovered pathophysiological states, and construct prediction models. There has been tremendous interest and increased incorporation of artificial intelligence into various industries, including healthcare. As a result, there has been an exponential rise in the number of research articles and industry participants producing models intended for a variety of applications in medical imaging, which can be challenging to navigate for radiologists. In thoracic imaging, multiple applications are being evaluated for chest radiography and computed tomography and include applications for lung nodule evaluation and cancer imaging, quantifying diffuse lung disorders, and cardiac imaging, to name a few. This review aims to provide an overview of current clinical AI models, focusing on the most common clinical applications of AI in cardiothoracic imaging.

The role of sphingolipid metabolism disruption on lipopolysaccharide-induced lung injury in mice.

AIM: This study assessed pulmonary outcomes generated by inhibiting key enzymes of sphingolipid metabolism pathways related to ceramide synthesis in a murine model of lung injury induced by lipopolysaccharide (LPS). METHODS: C57BL/6 male adult mice received LPS intratracheally and the expressions of acid sphingomyelinase (ASM), neutral sphingomyelinase (NSM), serine palmitoyl transferase (SPT) and dihydroceramide synthase (DS) were assessed at 2, 4, 6, 12 and 24 h after LPS instillation in lung homogenate (n = 30). The pharmacological inhibition of ASM, NSM, SPT and DS were assayed in other mice groups by three different doses of desipramine, GW4869, myriocin and fumonisin, respectively (n = 90). Their most effective doses were administered intraperitoneally 1 or 2 h before LPS to different animal groups (n = 120). Mice underwent determination of pulmonary mechanics, lung histopathological aspects and apoptosis. RESULTS: The expression levels of the enzymes reached their peak at 2-4 h after LPS administration. ASM inhibition attenuated alveolar collapse and GW4869 decreased lung elastance, proinflammatory cytokines' levels and was more effective to improve alveolar collapse than desipramine. On the other hand, SPT blockage aggravated lung lesion and no effects it was observed with fumonisin. Moreover, simultaneous administration of inhibitors (desipramine + GW4869, myriocin + fumonisin and all inhibitors together) resulted in no changes. CONCLUSION: Blockage of sphingomyelinases and the de novo pathways improved and aggravated lung injury, respectively, putatively suggesting specific targets to therapeutic strategies in LPS-induced lung injury.