Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Three-dimensional facial-image analysis to predict heterogeneity of the human ageing rate and the impact of lifestyle

Abstract

Not all individuals age at the same rate. Methods such as the ‘methylation clock’ are invasive, rely on expensive assays of tissue samples and infer the ageing rate by training on chronological age, which is used as a reference for prediction errors. Here, we develop models based on convoluted neural networks through training on non-invasive three-dimensional (3D) facial images of approximately 5,000 Han Chinese individuals that achieve an average difference between chronological or perceived age and predicted age of ±2.8 and 2.9 yr, respectively. We further profile blood transcriptomes from 280 individuals and infer the molecular regulators mediating the impact of lifestyle on the facial-ageing rate through a causal-inference model. These relationships have been deposited and visualized in the Human Blood Gene Expression—3D Facial Image (HuB-Fi) database. Overall, we find that humans age at different rates both in the blood and in the face, but do so coherently and with heterogeneity peaking at middle age. Our study provides an example of how artificial intelligence can be leveraged to determine the perceived age of humans as a marker of biological age, while no longer relying on prediction errors of chronological age, and to estimate the heterogeneity of ageing rates within a population.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Accuracy of age predictors, and the health parameters and lifestyles associated with AgeDiffs.
Fig. 2: AgeDiff heterogeneity peaks at middle age.
Fig. 3: Inflammation is related to AgeDiff at the molecular and cellular level.
Fig. 4: Inferred molecular mediators of AgeDiffs.

Data availability

The regulatory genes used in building the causal-inference network are from the KEGG pathway (https://www.genome.jp/kegg/pathway.html), Reactome (https://www.reactome.org/), Animal Transcription Factor Database (http://www.bioguo.org/AnimalTFDB/), human DEPhOsphorylation Database (http://www.depod.bioss.uni-freiburg.de/), IUPHAR/BPS database (http://www.guidetopharmacology.org/) and ImmPort42 (https://www.immport.org/shared/genelists). ImageNet (http://image-net.org/) was used for pretraining.

Results of facial-image, transcriptome and lifestyle associations are searchable at http://www.picb.ac.cn/hanlab/hub-fi/. Three-dimensional images and other metadata sensitive to personal identification cannot be publicized or shared according to our participant consent agreement. Individual sequencing raw data, as they contain genetic information, will be available on request under the condition of approval of the ethics committee of Shanghai Institute of Nutrition and Health, Chinese Academy of Sciences abiding China Human Genetic Resource law. Mapped read counts and FPKM expression values of coding genes from the RNA-seq are deposited to the public repository NODE at https://www.biosino.org/node/project/detail/OEP001041.

References

  1. 1.

    Peters, M. J. et al. The transcriptional landscape of age in human peripheral blood. Nat. Commun. 6, 8570 (2015).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  2. 2.

    Lehallier, B. et al. Undulating changes in human plasma proteome profiles across the lifespan. Nat. Med. 25, 1843–1850 (2019).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  3. 3.

    Hannum, G. et al. Genome-wide methylation profiles reveal quantitative views of human aging rates. Mol. Cell 49, 359–367 (2013).

    CAS  PubMed  Article  Google Scholar 

  4. 4.

    Horvath, S. DNA methylation age of human tissues and cell types. Genome Biol. 14, 3156 (2013).

    Article  Google Scholar 

  5. 5.

    Unschuld, P. U. & Tessenow, H. Huang Di Nei Jing Su Wen (University of California Press, 2011).

  6. 6.

    Chen, W., Xia, X., Huang, Y., Chen, X. & Han, J.-D. J. Bioimaging for quantitative phenotype analysis. Methods 102, 20–25 (2016).

    CAS  PubMed  Article  Google Scholar 

  7. 7.

    Chen, W. et al. Three-dimensional human facial morphologies as robust aging markers. Cell Res. 25, 574–587 (2015).

    PubMed  PubMed Central  Article  Google Scholar 

  8. 8.

    López-Otín, C., Blasco, M. A., Partridge, L., Serrano, M. & Kroemer, G. The Hallmarks of Aging. Cell 153, 1194–1217 (2013).

    PubMed  PubMed Central  Article  Google Scholar 

  9. 9.

    Gao, X. W., Hui, R. & Tian, Z. Classification of CT brain images based on deep learning networks. Computer Methods Programs Biomed. 138, 49–56 (2017).

    Article  Google Scholar 

  10. 10.

    Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).

    CAS  Article  Google Scholar 

  11. 11.

    Millstein, J., Zhang, B., Zhu, J. & Schadt, E. E. Disentangling molecular relationships with a causal inference test. BMC Genet. 10, 23 (2009).

    PubMed  PubMed Central  Article  Google Scholar 

  12. 12.

    Debrabant, B. et al. DNA methylation age and perceived age in elderly Danish twins. Mechanisms Ageing Dev. 169, 40–44 (2018).

    CAS  Article  Google Scholar 

  13. 13.

    Lu, T. et al. Gene regulation and DNA damage in the ageing human brain. Nature 429, 883–891 (2004).

    CAS  PubMed  Article  Google Scholar 

  14. 14.

    Newman, A. M. et al. Robust enumeration of cell subsets from tissue expression profiles. Nat. Methods 12, 453–457 (2015).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  15. 15.

    Jefferson, A. L. et al. Inflammatory biomarkers are associated with total brain volume. Neurology 68, 1032–1038 (2007).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  16. 16.

    Frąckiewicz, J. et al. Hematological parameters and all-cause mortality: a prospective study of older people. Aging Clin. Exp. Res. 30, 517–526 (2018).

    PubMed  Article  Google Scholar 

  17. 17.

    Chatthanawaree, W. Biomarkers of cobalamin (vitamin B12) deficiency and its application. J. Nutr. Health Aging 15, 227–231 (2011).

    CAS  PubMed  Article  Google Scholar 

  18. 18.

    Conigrave, K. M., Davies, P., Haber, P. & Whitfield, J. B. Traditional markers of excessive alcohol use. Addiction 98, 31–43 (2003).

    PubMed  Article  Google Scholar 

  19. 19.

    Liu, Y. et al. Epigenome-wide association data implicate DNA methylation as an intermediary of genetic risk in rheumatoid arthritis. Nat. Biotechnol. 31, 142–147 (2013).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  20. 20.

    Ahmed, Z. et al. Accelerated lipofuscinosis and ubiquitination in granulin knockout mice suggest a role for progranulin in successful aging. Am. J. Pathol. 177, 311–324 (2010).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  21. 21.

    He, Z., Ong, C. H. P., Halper, J. & Bateman, A. Progranulin is a mediator of the wound response. Nat. Med. 9, 225–229 (2003).

    CAS  PubMed  Article  Google Scholar 

  22. 22.

    Elkabets, M. et al. Human tumors instigate granulin-expressing hematopoietic cells that promote malignancy by activating stromal fibroblasts in mice. J. Clin. Invest 121, 784–799 (2011).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  23. 23.

    Chitramuthu, B. P., Bennett, H. P. J. & Bateman, A. Progranulin: a new avenue towards the understanding and treatment of neurodegenerative disease. Brain 140, 3081–3104 (2017).

    PubMed  Article  Google Scholar 

  24. 24.

    Knupp, D. & Miura, P. CircRNA accumulation: a new hallmark of aging? Mechanisms Ageing Dev. 173, 71–79 (2018).

    CAS  Article  Google Scholar 

  25. 25.

    Ruiz, R. et al. Sterol regulatory element-binding protein-1 (SREBP-1) is required to regulate glycogen synthesis and gluconeogenic gene expression in mouse liver. J. Biol. Chem. 289, 5510–5517 (2014).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  26. 26.

    Oishi, Y. et al. SREBP1 contributes to resolution of pro-inflammatory TLR4 signaling by reprogramming fatty acid metabolism. Cell Metab. 25, 412–427 (2017).

    CAS  PubMed  Article  Google Scholar 

  27. 27.

    Li, S. et al. Metabolic phenotypes of response to vaccination in humans. Cell 169, 862–877.e817 (2017).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  28. 28.

    Schoenborn, N. L. et al. Preferred clinician communication about stopping cancer screening among older US adults: results from a national survey. JAMA Oncol. 4, 1126–1128 (2018).

    PubMed  PubMed Central  Article  Google Scholar 

  29. 29.

    World Medical Association Inc Declaration of Helsinki. Ethical principles for medical research involving human subjects. J. Indian Med. Assoc. 107, 403–405 (2009).

    Google Scholar 

  30. 30.

    Guo, J., Mei, X. & Tang, K. Automatic landmark annotation and dense correspondence registration for 3D human facial images. BMC Bioinformatics 14, 232 (2013).

    PubMed  PubMed Central  Article  Google Scholar 

  31. 31.

    King, D. E. Dlib-ml: a Machine Learning Toolkit J. Mach. Learn. Res. 10, 1755–1758 (2009).

  32. 32.

    Szegedy, C. et al. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1–9 (2015).

  33. 33.

    Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. Preprint at https://https://arxiv.org/abs/1409.1556 (2014).

  34. 34.

    He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in IEEE Conference on Computer Vision and Pattern Recognition 770–778 (2016).

  35. 35.

    Kingma, D. & Ba, J. Adam: A method for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).

  36. 36.

    Harrow, J. et al. GENCODE: the reference human genome annotation for The ENCODE Project. Genome Res. 22, 1760–1774 (2012).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  37. 37.

    Trapnell, C. et al. Differential gene and transcript expression analysis of RNA-seq experiments with TopHat and Cufflinks. Nat. Protoc. 7, 562–578 (2012).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  38. 38.

    Zhang, X. O. et al. Diverse alternative back-splicing and alternative splicing landscape of circular RNAs. Genome Res. 26, 1277–1287 (2016).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  39. 39.

    Wold, S., Sjöström, M. & Eriksson, L. PLS-regression: a basic tool of chemometrics. Chemometrics Intell. Lab. Syst. 58, 109–130 (2001).

    CAS  Article  Google Scholar 

  40. 40.

    Subramanian, A. et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc. Natl Acad. Sci. USA 102, 15545–15550 (2005).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  41. 41.

    Dennis, G. et al. DAVID: database for annotation, visualization, and integrated discovery. Genome Biol. 4, P3 (2003).

    PubMed  Article  Google Scholar 

  42. 42.

    Bhattacharya, S. et al. ImmPort, toward repurposing of open access immunological assay data for translational and clinical research. Sci. Data 5, 180015 (2018).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  43. 43.

    Coppé, J.-P., Desprez, P.-Y., Krtolica, A. & Campisi, J. The senescence-associated secretory phenotype: the dark side of tumor suppression. Annu Rev. Pathol. 5, 99–118 (2010).

    PubMed  PubMed Central  Article  Google Scholar 

  44. 44.

    Millstein, J., Chen, G. K. & Breton, C. V. cit: hypothesis testing software for mediation analysis in genomic applications. Bioinformatics 32, 2364–2365 (2016).

    CAS  PubMed  PubMed Central  Article  Google Scholar 

Download references

Acknowledgements

This work was supported by grants from the National Natural Science Foundation of China (91749205), China Ministry of Science and Technology (2016YFE0108700) and Shanghai Municipal Science and Technology Major Project (2017SHZDZX01) to J.-D.J.H.

Author information

Affiliations

Authors

Contributions

J.-D.J.H. conceived and designed the study and analyses. Y.Z. set up the cohort and designed and collected baseline data. C.V.C., together with J.D.J.H., conceived the paradigm-shift idea to train the CNN on perceived age instead of chronological age for an AI-based perceived-age predictor. X.X. and X.C. analysed the data, with help from Y.W. and C.X. Y. Cao, W. Wei, G.C. Y.Y., X.X., K.L. and D.C. helped in collecting and preprocessing data. N.Q., X.Z. and J.J. helped to set up GPU, AI systems and training. G.W. and F.L. performed the PBMC-isolation and RNA-extraction experiments. Weiyang Chen provided FacePlsAge. B.X., Weizhong Chen, Y. Cao, C.X. and W.G. helped to recruit the Beijing cohorts. G.C. quantified the wrinkle and symmetry on faces. Y. Chen analysed circRNA. X.W., M.C. and D.C. helped with data analysis. X.X., X.C., J.D.J.H, C.V.C., K.Z., B.K.K. and W. Wang wrote the manuscript. All authors contributed to preparation of the manuscript. G.W., F.L. and Y.W. contributed equally.

Corresponding authors

Correspondence to Yong Zhou or Jing-Dong J. Han.

Ethics declarations

Competing interests

Authors declare no competing interests.

Additional information

Peer review information Primary Handling Editor: Pooja Jha.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Age and perceived age prediction using CNN.

a, Deep learning performance in training, validation and testing datasets for age prediction. Average loss (mean average difference (MAD), upper panel) and accuracy (Pearson Correlation Coefficient (PCC), lower panel) were plotted over training epochs. One epoch indicates the network weights updates over the whole training dataset for one time. b, Overlap between FaceCnnAge, FaceCnnPerceivedAge, FacePerceivedAge, and FacePlsAge in younger (left), normal (middle), and older (right) samples. The lower table shows the one-tailed Fisher’s exact test p-values with light red indicate p < 0.05. c, d, Independent validation of FaceCnnAge (c) and FaceCnnPerceivedAge (d) on 332 facial images collected in Beijing, 2012 (left) and 358 facial images collected in Beijing, 2015 (right).

Extended Data Fig. 2 AgeDiff-associated lifestyles in Beijing (2012) cohort by ANOVA test.

The p value is derived from ANOVA (n=341). All results with p < 0.05 are shown here. Data are presented as mean +/- SD.

Extended Data Fig. 3 Heterogeneity of aging rate at different ages in Jidong and Beijing cohort.

a, The standard deviation of randomly guess a number between 20–85 (n=4719, the boxes show 25%, 50% and 75% quantile and whiskers show maximum and minimum value). b, Relationship between age and the standard deviation of four AgeDiffs with bin size as 20 in Jidong cohort. Data are presented as mean +/- SD. c, Heatmap of aging-related facial features, health parameters and RNAs in Beijing (2012) cohort sorted by increasing chronological age (PCC with age, FDR < 0.05). Features were ranked by PCC from low to high (ALB: albumin, A/G: albumin/ globulin, TP: total protein, GGT: glutamyl transpeptidase, ALP: alkline phosphatase, CREA: creatinine, CHO: total cholesterol). d, e, Relationship between age and the standard deviation of four AgeDiffs with bin size as 20 (d) and 10 (e) in Beijing (2012) cohort. Data are presented as mean +/- SD.

Extended Data Fig. 4 Broken stick regression of SD of AgeDiffs against age.

a, b, Broken stick regression in Jidong cohort with bin size 100 (a) and 20 (b). c, d, Broken stick regression in Beijing (2012) cohort with bin size 20 (c) and 10 (d).

Extended Data Fig. 5 Age prediction using transcriptome.

a–c, Mean absolute difference (MAD) (top panel), Pearson correlation coefficient (PCC) (bottom panel) saturation analysis and correlation against chronological age of transcriptomes PLS age prediction for all the samples (a), female (b) and male (c), respectively. d, Enriched GO biological processes terms of PLS top 10% (upper) or 20% (lower) loading genes. P values are derived from hypergeometric test (Methods). e, Overlap between FacePlsAge, FaceCnnAge, RnaPlsAge, and FaceCnnPerceivedAge in younger (left), normal (middle), and older (right) samples. The lower table shows the one-tailed Fisher’s exact test p-values with light red highlight indicate p < 0.05.

Extended Data Fig. 6 Associations between cell types and AgeDiffs.

a, Cytokines (left panels) and antigen processing and presentation (right panels) enrichment scores as a function of four AgeDiffs. P values are derived from permutation test (Methods). b, Association of RNA-seq deconvoluted cell type fractions and AgeDiffs (* p<0.1, ** p<0.05, *** p<0.01 derived from two-sided t test, and * Benjamini-Hochberg correction derived FDR < 0.1).

Extended Data Fig. 7 Expression profile of expressed non-coding RNAs against chronological age.

a, The heatmap of expressed lncRNAs (FPKM > 2) significantly related to chronological age (FDR < 0.1). The samples (columns) were sorted by age and lncRNAs were sorted by PCC of expression to age from high to low. b, The heatmap of expressed circRNAs (TPM > 2) significantly related to chronological age (FDR < 0.1). The samples (columns) were sorted by age and circRNAs were sorted by PCC of expression to age from high to low. c, Top three enriched terms for parent genes of age-up (top) and age-down circRNAs. P values are derived from hypergeometric test (Methods). d, The correlation between age and total expression level of circRNAs. P value is derived from two-sided t test.

Supplementary information

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xia, X., Chen, X., Wu, G. et al. Three-dimensional facial-image analysis to predict heterogeneity of the human ageing rate and the impact of lifestyle. Nat Metab 2, 946–957 (2020). https://doi.org/10.1038/s42255-020-00270-x

Download citation

Further reading

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing