The high incidence of barotrauma in patients with COVID-19-related acute respiratory distress syndrome (ARDS) (16.1%, with a mortality rate \>60%) provides rationale for considering COVID-19 ARDS a paradigm for lung frailty. The investigators recently discovered that the Macklin effect is an impressive radiological predictor of barotrauma in COVID-19 ARDS. Since lung frailty is a major issue also in non-COVID-19 ARDS (6% barotrauma, with a mortality rate of 46% ) the investigators want to confirm the importance of Macklin effect in non-COVID-19 ARDS. Using artificial intelligence-based approaches the investigators also want to identify imaging biomarkers to non-invasively assess lung frailty in a mixed cohort of COVID-19/non-COVID-19 ARDS patients. Furthermore, the investigators want to prospectively validate these biomarkers in a cohort of ARDS patients. This will provide a therapeutic algorithm for ARDS patients at high-risk for barotrauma, identifying those most likely to benefit from hyper protective strategies.