Deep Learning Shows Cellular Senescence Is a Barrier to Cancer Development

Abstract

Cellular senescence is a critical component of aging and many age-related diseases, but understanding its role in human health is challenging in part due to the lack of exclusive or universal markers. Using neural networks, we achieve high accuracy in predicting senescence state and type from the nuclear morphology of DAPI-stained human fibroblasts, murine astrocytes and fibroblasts derived from premature aging diseases in vitro. After generalizing this approach, the predictor recognizes an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating corresponding medical records reveals that individuals with increased senescent cells have a significantly decreased rate of malignant neoplasms, lending support for the protective role of senescence in limiting cancer development. In sum, we introduce a novel predictor of cellular senescence and apply it to diagnostic medical images, indicating cancer occurs more frequently for those with a lower rate of senescence.