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.

  • Brief Communication
  • Published:

Industry research

Novel body fat estimation using machine learning and 3-dimensional optical imaging

European Journal of Clinical Nutrition volume 74, pages 842–845 (2020)Cite this article

Subjects

Abstract

Estimates of body composition have been derived using 3-dimensional optical imaging (3DO), but no equations to date have been calibrated using a 4-component (4C) model criterion. This investigation reports the development of a novel body fat prediction formula using anthropometric data from 3DO imaging and a 4C model. Anthropometric characteristics and body composition of 179 participants were measured via 3DO (Size Stream® SS20) and a 4C model. Machine learning was used to identify significant anthropometric predictors of body fat (BF%), and stepwise/lasso regression analyses were employed to develop new 3DO-derived BF% prediction equations. The combined equation was externally cross-validated using paired 3DO and DXA assessments (n = 158), producing a R2 value of 0.78 and a constant error of (X ± SD) 0.8 ± 4.5%. 3DO BF% estimates demonstrated equivalence with DXA based on equivalence testing with no proportional bias in the Bland–Altman analysis. Machine learning methods may hold potential for enhancing 3DO-derived BF% estimates.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Decision tree analysis.
Fig. 2: Validation of 3DO body fat estimates.

Similar content being viewed by others

References

  1. Ng BK, Sommer MJ, Wong MC, Pagano I, Nie Y, Fan B et al. Detailed 3-dimensional body shape features predict body composition, blood metabolites, and functional strength: the Shape Up! studies. Am J Clin Nutr. 2019. https://doi.org/10.1093/ajcn/nqz218.

  2. Tinsley GM, Moore ML, Benavides ML, Dellinger JR, Adamson BT. 3-Dimensional optical scanning for body composition assessment: a 4-component model comparison of four commercially available scanners. Clin Nutr 2020. https://doi.org/10.1016/j.clnu.2020.02.008.

  3. Wong MC, Ng BK, Kennedy SF, Hwaung P, Liu EY, Kelly NN, et al. Children and adolescents’ anthropometrics body composition from 3-D optical surface scans. Obesity. 2019;27:1738–49. https://doi.org/10.1002/oby.22637.

    Article  PubMed  Google Scholar 

  4. Heymsfield SB, Bourgeois B, Ng BK, Sommer MJ, Li X, Shepherd JA. Digital anthropometry: a critical review. Eur J Clin Nutr. 2018;72:680–7. https://doi.org/10.1038/s41430-018-0145-7.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Tinsley GM, Moore ML, Dellinger JR, Adamson BT, Benavides ML. Digital anthropometry via three-dimensional optical scanning: evaluation of four commercially available systems. Eur J Clin Nutr. 2019. https://doi.org/10.1038/s41430-019-0526-6.

    Article  PubMed  Google Scholar 

  6. Harbin MM, Kasak A, Ostrem JD, Dengel DR. Validation of a three-dimensional body scanner for body composition measures. Eur J Clin Nutr. 2018;72:1191–4. https://doi.org/10.1038/s41430-017-0046-1.

    Article  PubMed  Google Scholar 

  7. Wang ZM, Xavier P-S, Kotler DP, Wielopolski L, Withers RT, Pierson J, et al. Multicomponent methods: Evaluation of new and traditional soft tissue mineral models by in vivo neutron activation analysis. Am J Clin Nutr. 2002;76:968–74.

    Article  CAS  Google Scholar 

  8. Shepherd JA, Fan B, Lu Y, Wu XP, Wacker WK, Ergun DL, et al. A multinational study to develop universal standardization of whole-body bone density and composition using GE Healthcare Lunar and Hologic DXA systems. J Bone Min Res. 2012;27:2208–16. https://doi.org/10.1002/jbmr.1654.

    Article  Google Scholar 

  9. Dixon PM, Saint-Maurice PF, Kim Y, Hibbing P, Bai Y, Welk GJ. A primer on the use of equivalence testing for evaluating measurement agreement. Med Sci sports Exerc. 2018;50:837–45. https://doi.org/10.1249/mss.0000000000001481.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Ryder JR, Ball SD. Three-dimensional body scanning as a novel technique for body composition assessment: a preliminary investigation. J Exerc Physiol Online. 2012;15:1.

    Google Scholar 

  11. Wang J, Gallagher D, Thornton JC, Yu W, Horlick M, Pi-Sunyer FX. Validation of a 3-dimensional photonic scanner for the measurement of body volumes, dimensions, and percentage body fat. Am J Clin Nutr. 2006;83:809–16.

    Article  CAS  Google Scholar 

Download references

Funding

No funding was received for the data collection leading to equation development, although the project was supported in-kind by Size Stream, LLC through provision of the 3-dimensional optical scanner. The data utilized for external validation were obtained from research supported by the National Institute of Diabetes and Digestive and Kidney Diseases (R01DK109008, R01DK111698) and registered at Clinical Trial Registration: NCT03637855.

Author information

Authors and Affiliations

  1. Energy Balance & Body Composition Laboratory; Department of Kinesiology & Sport Management, Texas Tech University, Lubbock, TX, USA

    Patrick S. Harty, Matthew T. Stratton & Grant M. Tinsley

  2. Size Stream LLC, Cary, NC, USA

    Breck Sieglinger & David Bruner

  3. Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LA, USA

    Steven B. Heymsfield

  4. Department of Epidemiology and Population Science, University of Hawaii Cancer Center, Honolulu, HI, USA

    John A. Shepherd

Authors
  1. Patrick S. Harty
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Breck Sieglinger
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Steven B. Heymsfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. John A. Shepherd
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. David Bruner
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Matthew T. Stratton
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Grant M. Tinsley
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

PSH interpreted results, prepared the paper, and reviewed the paper; BS performed data analyses, interpreted results, and reviewed the paper; SBH and JAS supervised data collection, interpreted results, and reviewed the paper; DB and MTS interpreted results and reviewed the paper; GMT supervised data collection, performed data analyses, interpreted results, prepared the paper, and reviewed the paper. All authors read and approved the submitted paper.

Corresponding author

Correspondence to Grant M. Tinsley.

Ethics declarations

Conflict of interest

Size Stream, LLC, the manufacturer of the 3D scanner utilized in the present study, supported the project through equipment loan/donation to the study sites. However, monetary funding was not provided to the study sites or investigators as part of this project. Size Stream, LLC was also involved in the study design, execution, analysis, and interpretation of the study results. DB is employed by Size Stream, LLC, and BS is a paid analysis consultant for Size Stream, LLC. SBH is on the medical advisory board for Tanita Medical. JAS has received in-kind support from Size Stream, LLC, Styku, and FIT3D and has received research funding from Hologic and General Electric (GE) Healthcare. GMT has received in-kind support from Size Stream, LLC, Naked Labs Inc., RJL Systems, MuscleSound, and Biospace, Inc. (DBA InBody). The remaining authors declare no potential conflicts of interest.

Additional information

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Harty, P.S., Sieglinger, B., Heymsfield, S.B. et al. Novel body fat estimation using machine learning and 3-dimensional optical imaging. Eur J Clin Nutr 74, 842–845 (2020). https://doi.org/10.1038/s41430-020-0603-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41430-020-0603-x

This article is cited by

Search

Advanced search

Quick links