Acute hypoxemic respiratory failure is a critical challenge in intensive care. A substantial proportion of patients present with asymmetric acute lung injury (ALI), complicating management due to heterogeneous lung involvement. While lung-protective mechanical ventilation represents the standard of care, the optimal approach to positive end-expiratory pressure (PEEP) titration remains unclear. This study investigated the effects of transpulmonary pressure (TPP)-guided PEEP titration vs. a fixed PEEP strategy in a porcine model of unilateral ALI. A total of 14 pigs underwent ALI induction via unilateral surfactant depletion and were randomized to receive either a fixed PEEP of 5 cmH₂O or a PEEP targeting a slightly positive TPP at end-expiration. Over six hours, respiratory mechanics, high-resolution computed tomography (HRCT), histological lung injury scores (LIS), and plasma protein biomarkers were assessed. TPP-guided PEEP titration significantly lowered driving pressure and improved compliance compared to fixed low PEEP, suggesting more homogeneous tidal volume distribution. HRCT revealed less collateral injury in the initially non-injured lung in the TPP-guided group. However, histopathological LIS did not differ between groups. Exploratory cytokine profiling showed systemic inflammatory activation—including pro- and anti-inflammatory responses—only in the TPP-guided group. These findings indicate that TPP-guided PEEP titration may optimize ventilation by balancing alveolar recruitment and overdistension in asymmetric ALI, with clear effects on physiological and imaging parameters, but without parallel effects on cytokine responses. Further research is needed to assess its long-term impact and clinical relevance.

Background: In this study focusing on colorectal carcinoma (CRC), we address the imperative task of predicting post-surgery treatment needs by identifying crucial tumor features within whole slide images of solid tumors, analogous to locating a needle in a histological haystack. We evaluate two approaches to address this challenge using a small CRC dataset. Methods: First, we explore a conventional tile-level training approach, testing various data augmentation methods to mitigate the memorization effect in a noisy label setting. Second, we examine a multi-instance learning (MIL) approach at the case level, adapting data augmentation techniques to prevent over-fitting in the limited data set context. Results: The tile-level approach proves ineffective due to the limited number of informative image tiles per case. Conversely, the MIL approach demonstrates success for the small dataset when coupled with post-feature vector creation data augmentation techniques. In this setting, the MIL model accurately predicts nodal status corresponding to expert-based budding scores for these cases. Conclusions: This study incorporates data augmentation techniques into a MIL approach, highlighting the effectiveness of the MIL method in detecting predictive factors such as tumor budding, despite the constraints of a limited dataset size.

Early detection of acute lung injury (ALI) remains challenging, as conventional diagnostics rarely capture initial molecular changes. We therefore examined whether extracellular vesicles (EVs) in bronchoalveolar lavage fluid (BALF) can detect early regional injury and distinguish initial stress mechanisms in a porcine ALI model. Unilateral ALI was induced using Triton X-100, followed by six hours of mechanical ventilation with either fixed positive end-expiratory pressure (PEEP) at 5 cmH₂O or transpulmonary-pressure (TPP)-guided PEEP. Spatially separated BALF sampling allowed direct comparison between injured and contralateral mechanically stressed lungs. EV concentration and size distribution were quantified by nano-flow cytometry, while vesicular identity was confirmed by transmission electron microscopy and tetraspanin dot blot analyses. Furthermore, EV metrics were related to corresponding histologic injury scores. Across both PEEP strategies, EV concentration was markedly higher in both directly injured and contralateral mechanically stressed lungs compared with sham controls, indicating alveolar stress beyond the primary injury site. Median EV size differed significantly by injury type and correlated inversely with histologic injury, particularly with alveolar neutrophil infiltration. BALF-derived EV concentration and size may therefore provide complementary, spatially resolved molecular readouts of early ALI.