Nuclear morphology is a deep learning biomarker of cellular senescence

Senescent cells are typically identified by a combination of senescence-associated markers, and the phenotype is heterogeneous. Here, using deep neural networks, Heckenbach et al. show that nuclear morphology can be used to predict cellular senescence in images of tissues and cell cultures. Cellular senescence is an important factor in aging and many age-related diseases, but understanding its role in health is challenging due to the lack of exclusive or universal markers. Using neural networks, we predict senescence from the nuclear morphology of human fibroblasts with up to 95% accuracy, and investigate murine astrocytes, murine neurons, and fibroblasts with premature aging in culture. After generalizing our approach, the predictor recognizes higher rates of senescence in p21-positive and ethynyl-2'-deoxyuridine (EdU)-negative nuclei in tissues and shows an increasing rate of senescent cells with age in H&E-stained murine liver tissue and human dermal biopsies. Evaluating medical records reveals that higher rates of senescent cells correspond to decreased rates of malignant neoplasms and increased rates of osteoporosis, osteoarthritis, hypertension and cerebral infarction. In sum, we show that morphological alterations of the nucleus can serve as a deep learning predictor of senescence that is applicable across tissues and species and is associated with health outcomes in humans.

Automated summary

A deep learning predictor based on nuclear morphology can identify senescent cells and is associated with health outcomes in humans.