Search for: All records

Dysregulation of lung tissue collagen level plays a vital role in understanding how lung diseases progress. However, traditional scoring methods rely on manual histopathological examination introducing subjectivity and inconsistency into the assessment process. These methods are further hampered by inter-observer variability, lack of quantification, and their time-consuming nature. To mitigate these drawbacks, we propose a machine learning-driven framework for automated scoring of lung collagen content. Our study begins with the collection of a lung slide image dataset from adult female mice using second harmonic generation (SHG) microscopy. In our proposed approach, first, we manually extracted features based on the 46 statistical parameters of fibrillar collagen. Subsequently, we pre-processed the images and utilized a pre-trained VGG16 model to uncover hidden features from pre-processed images. We then combined both image and statistical features to train various machine learning and deep neural network models for classification tasks. We employed advanced unsupervised techniques like K-means, principal component analysis (PCA), t-distributed stochastic neighbour embedding (t-SNE), and uniform manifold approximation and projection (UMAP) to conduct thorough image analysis for lung collagen content. Also, the evaluation of the trained models using the collagen data includes both binary and multi-label classification to predict lung cancer in a urethane-induced mouse model. Experimental validation of our proposed approach demonstrates promising results. We obtained an average accuracy of 83% and an area under the receiver operating characteristic curve (ROC AUC) values of 0.96 through the use of a support vector machine (SVM) model for binary categorization tasks. For multi-label classification tasks, to quantify the structural alteration of collagen, we attained an average accuracy of 73% and ROC AUC values of 1.0, 0.38, 0.95, and 0.86 for control, baseline, treatment_1, and treatment_2 groups, respectively. Our findings provide significant potential for enhancing diagnostic accuracy, understanding disease mechanisms, and improving clinical practice using machine learning and deep learning models. 

Abstract Approximately 7% of pregnant women in the United States use electronic-cigarette (e-cig) devices during pregnancy. There is, however, no scientific evidence to support e-cig use as being ‘safe’ during pregnancy. Little is known about the effects of fetal exposures to e-cig aerosols on lung alveologenesis. In the present study, we tested the hypothesis that in utero exposure to e-cig aerosol impairs lung alveologenesis and pulmonary function in neonates. Pregnant BALB/c mice were exposed 2 h a day for 20 consecutive days during gestation to either filtered air or cinnamon-flavored e-cig aerosol (36 mg/mL of nicotine). Lung tissue was collected in offspring during lung alveologenesis on postnatal day (PND) 5 and PND11. Lung function was measured at PND11. Exposure to e-cig aerosol in utero led to a significant decrease in body weights at birth which was sustained through PND5. At PND5, in utero e-cig exposures dysregulated genes related to Wnt signaling and epigenetic modifications in both females (~ 120 genes) and males (40 genes). These alterations were accompanied by reduced lung fibrillar collagen content at PND5—a time point when collagen content is close to its peak to support alveoli formation. In utero exposure to e-cig aerosol also increased the Newtonian resistance of offspring at PND11, suggesting a narrowing of the conducting airways. At PND11, in females, transcriptomic dysregulation associated with epigenetic alterations was sustained (17 genes), while WNT signaling dysregulation was largely resolved (10 genes). In males, at PND11, the expression of only 4 genes associated with epigenetics was dysregulated, while 16 Wnt related-genes were altered. These data demonstrate that in utero exposures to cinnamon-flavored e-cig aerosols alter lung structure and function and induce sex-specific molecular signatures during lung alveologenesis in neonatal mice. This may reflect epigenetic programming affecting lung disease development later in life. 

Matrix metalloproteinase-12 ( Mmp12 ) is upregulated by cigarette smoke (CS) and plays a critical role in extracellular matrix remodeling, a key mechanism involved in physiological repair processes, and in the pathogenesis of emphysema, asthma, and lung cancer. While cigarette smoking is associated with the development of chronic obstructive pulmonary diseases (COPD) and lung cancer, in utero exposures to CS and second-hand smoke (SHS) are associated with asthma development in the offspring. SHS is an indoor air pollutant that causes known adverse health effects; however, the mechanisms by which in utero SHS exposures predispose to adult lung diseases, including COPD, asthma, and lung cancer, are poorly understood. In this study, we tested the hypothesis that in utero SHS exposure aggravates adult-induced emphysema, asthma, and lung cancer. Methods: Pregnant BALB/c mice were exposed from gestational days 6–19 to either 3 or 10mg/m 3 of SHS or filtered air. At 10, 11, 16, or 17weeks of age, female offspring were treated with either saline for controls, elastase to induce emphysema, house-dust mite (HDM) to initiate asthma, or urethane to promote lung cancer. At sacrifice, specific disease-related lung responses including lung function, inflammation, gene, and protein expression were assessed. Results: In the elastase-induced emphysema model, in utero SHS-exposed mice had significantly enlarged airspaces and up-regulated expression of Mmp12 (10.3-fold compared to air-elastase controls). In the HDM-induced asthma model, in utero exposures to SHS produced eosinophilic lung inflammation and potentiated Mmp12 gene expression (5.7-fold compared to air-HDM controls). In the lung cancer model, in utero exposures to SHS significantly increased the number of intrapulmonary metastases at 58weeks of age and up-regulated Mmp12 (9.3-fold compared to air-urethane controls). In all lung disease models, Mmp12 upregulation was supported at the protein level. Conclusion: Our findings revealed that in utero SHS exposures exacerbate lung responses to adult-induced emphysema, asthma, and lung cancer. Our data show that MMP12 is up-regulated at the gene and protein levels in three distinct adult lung disease models following in utero SHS exposures, suggesting that MMP12 is central to in utero SHS-aggravated lung responses.