A Multi-omic Analysis of the Human Lung Reveals Distinct Cell Specific Aging and Senescence Molecular Programs

Age is a major risk factor for lung disease. To understand the mechanisms underlying this association, we characterized the changing cellular, genomic, transcriptional, and epigenetic landscape of lung aging using bulk and single-cell RNAseq (scRNAseq) data. Our analysis revealed age-associated gene networks that reflected hallmarks of aging, including mitochondrial dysfunction, inflammation, and cellular senescence. Cell type deconvolution revealed age-associated changes in the cellular composition of the lung: decreased alveolar epithelial cells and increased fibroblasts and endothelial cells. In the alveolar microenvironment, aging is characterized by decreased AT2B cells and reduced surfactant production, a finding that was validated by scRNAseq and IHC. We showed that a previously reported senescence signature, SenMayo, captures cells expressing canonical senescence markers. SenMayo signature also identified cell-type specific senescence-associated co-expression modules that have distinct molecular functions, including ECM regulation, cell signaling, and damage response pathways. Analysis of somatic mutations showed that burden was highest in lymphocytes and endothelial cells and was associated with high expression of senescence signature. Finally, aging and senescence gene expression modules were associated with differentially methylated regions, with inflammatory markers such as IL1B, IL6R, and TNF being significantly regulated with age. Our findings provide new insights into the mechanisms underlying lung aging and may have implications for the development of interventions to prevent or treat age-related lung diseases.

Hybrid Neural Networks for Mortality Prediction from LDCT Images

Known for its high morbidity and mortality rates, lung cancer poses a significant threat to human health and well-being. However, the same population is also at high risk for other deadly diseases, such as cardiovascular disease. Since Low-Dose CT (LDCT) has been shown to significantly improve the lung cancer diagnosis accuracy, it will be very useful for clinical practice to predict the all-cause mortality for lung cancer patients to take corresponding actions. In this paper, we propose a deep learning based method, which takes both chest LDCT image patches and coronary artery calcification risk scores as input to predict the mortality risk of lung cancer subjects. The proposed method is called Hybrid Risk Network (HyRiskNet) for mortality risk prediction, which is an end-to-end framework utilizing hybrid imaging features, instead of completely relying on automatic feature extraction. Our work demonstrates the feasibility of using deep learning techniques for all-cause lung cancer mortality prediction from chest LDCT images. The experimental results show that HyRiskNet can achieve superior performance compared with the neural networks with only image input and with other traditional semi-automatic scoring methods. The study also indicates that radiologist defined features can well complement convolutional neural networks for more comprehensive feature extraction.

Comparison of deep learning and human observer performance for detection and characterization of simulated lesions

Detection and characterization of abnormalities in clinical imaging are of utmost importance for patient diagnosis and treatment. We present a comparison of convolutional neural network (CNN) and human observer performance on a simulated lesion detection and characterization task. We apply both conventional performance metrics, including accuracy and nonconventional metrics such as lift charts to perform qualitative and quantitative comparisons of each type of observer. It is determined that the CNN generally outperforms the human observers, particularly at high noise levels. However, high noise correlation reduces the relative performance of the CNN, and human observer performance is comparable to CNN under these conditions. These findings extend into the field of diagnostic radiology, where the adoption of deep learning is starting to become widespread. Consideration of the applications for which deep learning is most effective is of critical importance to this development.