RESUMEN
Fluorescence intravital microscopy captures large data sets of dynamic multicellular interactions within various organs such as the lungs, liver, and brain of living subjects. In medical imaging, edge detection is used to accurately identify and delineate important structures and boundaries inside the images. To improve edge sharpness, edge detection frequently requires the inclusion of low-level features. Herein, a machine learning approach is needed to automate the edge detection of multicellular aggregates of distinctly labeled blood cells within the microcirculation. In this work, the Structured Adaptive Boosting Trees algorithm (AdaBoost.S) is proposed as a contribution to overcome some of the edge detection challenges related to medical images. Algorithm design is based on the observation that edges over an image mask often exhibit special structures and are interdependent. Such structures can be predicted using the features extracted from a bigger image patch that covers the image edge mask. The proposed AdaBoost.S is applied to detect multicellular aggregates within blood vessels from the fluorescence lung intravital images of mice exposed to e-cigarette vapor. The predictive capabilities of this approach for detecting platelet-neutrophil aggregates within the lung blood vessels are evaluated against three conventional machine learning algorithms: Random Forest, XGBoost and Decision Tree. AdaBoost.S exhibits a mean recall, F-score, and precision of 0.81, 0.79, and 0.78, respectively. Compared to all three existing algorithms, AdaBoost.S has statistically better performance for recall and F-score. Although AdaBoost.S does not outperform Random Forest in precision, it remains superior to the XGBoost and Decision Tree algorithms. The proposed AdaBoost.S is widely applicable to analysis of other fluorescence intravital microscopy applications including cancer, infection, and cardiovascular disease.
RESUMEN
Despite the perception that e-cigarettes are safer than conventional cigarettes, numerous findings demonstrated that e-cigarette aerosol (EC) exposure induced compromised immune functionality, vascular changes even after acute exposure, and lung injury. Notably, altered neutrophil functionality and platelet hemodynamics have been observed post-EC exposure. It was hypothesized that EC exposure initiates an inflammatory response resulting in altered neutrophil behavior and increased neutrophil-platelet interaction in the pulmonary microvasculature. Neutrophil and platelet responses were examined up to 48 hrs following whole-body, short-term EC exposure without flavorants or nicotine in a murine model, which most closely modeled secondhand exposure. This study is the first to investigate the impact of EC exposure through lung intravital imaging. Compared to room air-exposed mice, EC-exposed mice displayed significantly increased 1.7â1.9-fold number of neutrophils in the pulmonary microvasculature associated with no marked change in neutrophils within whole blood or bronchoalveolar lavage fluid (BALF). Neutrophil-platelet interactions were also significantly elevated 1.9â2.5-fold in exposed mice. Plasma concentration of myeloperoxidase was markedly reduced 1.5-fold 48 hr following exposure cessation, suggesting suppressed neutrophil antimicrobial activity. Cytokine expression exhibited changes indicating vascular damage. Effects persisted for 48 hr post-EC exposure. Data demonstrated that EC exposure repeated for 3 consecutive days in 2.5 hr intervals in the absence of flavorants or nicotine resulted in modified pulmonary vasculature hemodynamics, altered immune functionality, and a pro-inflammatory state in female BALB/cJ mice.