Nuclear morphology is a deep learning biomarker of cellular senescence

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Nuclear morphology is a deep learning biomarker of cellular senescence. / Heckenbach, Indra; Mkrtchyan, Garik V.; Ezra, Michael Ben; Bakula, Daniela; Madsen, Jakob Sture; Nielsen, Malte Hasle; Oró, Denise; Osborne, Brenna; Covarrubias, Anthony J.; Idda, M. Laura; Gorospe, Myriam; Mortensen, Laust; Verdin, Eric; Westendorp, Rudi; Scheibye-Knudsen, Morten.

In: Nature Aging, Vol. 2, No. 8, 2022, p. 742-755.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Heckenbach, I, Mkrtchyan, GV, Ezra, MB, Bakula, D, Madsen, JS, Nielsen, MH, Oró, D, Osborne, B, Covarrubias, AJ, Idda, ML, Gorospe, M, Mortensen, L, Verdin, E, Westendorp, R & Scheibye-Knudsen, M 2022, 'Nuclear morphology is a deep learning biomarker of cellular senescence', Nature Aging, vol. 2, no. 8, pp. 742-755. https://doi.org/10.1038/s43587-022-00263-3

APA

Heckenbach, I., Mkrtchyan, G. V., Ezra, M. B., Bakula, D., Madsen, J. S., Nielsen, M. H., Oró, D., Osborne, B., Covarrubias, A. J., Idda, M. L., Gorospe, M., Mortensen, L., Verdin, E., Westendorp, R., & Scheibye-Knudsen, M. (2022). Nuclear morphology is a deep learning biomarker of cellular senescence. Nature Aging, 2(8), 742-755. https://doi.org/10.1038/s43587-022-00263-3

Vancouver

Heckenbach I, Mkrtchyan GV, Ezra MB, Bakula D, Madsen JS, Nielsen MH et al. Nuclear morphology is a deep learning biomarker of cellular senescence. Nature Aging. 2022;2(8):742-755. https://doi.org/10.1038/s43587-022-00263-3

Author

Heckenbach, Indra ; Mkrtchyan, Garik V. ; Ezra, Michael Ben ; Bakula, Daniela ; Madsen, Jakob Sture ; Nielsen, Malte Hasle ; Oró, Denise ; Osborne, Brenna ; Covarrubias, Anthony J. ; Idda, M. Laura ; Gorospe, Myriam ; Mortensen, Laust ; Verdin, Eric ; Westendorp, Rudi ; Scheibye-Knudsen, Morten. / Nuclear morphology is a deep learning biomarker of cellular senescence. In: Nature Aging. 2022 ; Vol. 2, No. 8. pp. 742-755.

Bibtex

@article{ac9bb6e691504e4caf560e5cbec953a9,

title = "Nuclear morphology is a deep learning biomarker of cellular senescence",

abstract = "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{\textquoteright}-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.",

author = "Indra Heckenbach and Mkrtchyan, {Garik V.} and Ezra, {Michael Ben} and Daniela Bakula and Madsen, {Jakob Sture} and Nielsen, {Malte Hasle} and Denise Or{\'o} and Brenna Osborne and Covarrubias, {Anthony J.} and Idda, {M. Laura} and Myriam Gorospe and Laust Mortensen and Eric Verdin and Rudi Westendorp and Morten Scheibye-Knudsen",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

doi = "10.1038/s43587-022-00263-3",

language = "English",

volume = "2",

pages = "742--755",

journal = "Nature Aging",

issn = "2662-8465",

publisher = "Nature Research",

number = "8",

}

RIS

TY - JOUR

T1 - Nuclear morphology is a deep learning biomarker of cellular senescence

AU - Heckenbach, Indra

AU - Mkrtchyan, Garik V.

AU - Ezra, Michael Ben

AU - Bakula, Daniela

AU - Madsen, Jakob Sture

AU - Nielsen, Malte Hasle

AU - Oró, Denise

AU - Osborne, Brenna

AU - Covarrubias, Anthony J.

AU - Idda, M. Laura

AU - Gorospe, Myriam

AU - Mortensen, Laust

AU - Verdin, Eric

AU - Westendorp, Rudi

AU - Scheibye-Knudsen, Morten

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

U2 - 10.1038/s43587-022-00263-3

DO - 10.1038/s43587-022-00263-3

M3 - Journal article

C2 - 37118134

AN - SCOPUS:85136018789

VL - 2

SP - 742

EP - 755

JO - Nature Aging

JF - Nature Aging

SN - 2662-8465

IS - 8

ER -

ID: 319160602

Center for Healthy Aging