Using computer vision to develop clinically accessible methods of human shape measurement - Joint PhD Programme with La Trobe University, Australia at Sheffield Hallam University on FindAPhD.com

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities

Dr Simon Choppin, Dr A Bullas No more applications being accepted Competition Funded PhD Project (Students Worldwide)

Sheffield United Kingdom Computer Vision Data Science Health Informatics Machine Learning

About the Project

Measurement of a person’s size is, typically, a fundamental practice in health assessment. Waist girth is used to determine an individual’s risk to conditions associated with obesity and metabolic syndrome (type 2 diabetes, cardiovascular disease). However, waist girth is a blunt tool that misses a significant sub-population of normal weight, metabolically obese individuals. As a result, treatment can be ineffective or even absent.

We have developed a method of measuring a person’s shape as well as their size. Our method extracts complex shape parameters from 3D body scanner of their torso. We have shown that our measures of shape contain additional information compared to size alone, and that they improve predictions of fat amount and distribution (which are closely related to metabolic syndrome).

In order to measure a person’s shape we currently require large, high-cost body scanning equipment. In order for shape measurement to have future practical applications we must develop more accessible methods of measurement. We want to develop quicker and lower cost methods of measuring shape so that they can be used routinely in clinical practice.

We would expect the student to formulate appropriate aims and objectives, however, we have included a possible aim and project structure below to provide context.

The aim of this PhD is to develop a low-cost, clinically accessible method of torso shape measurement.

The project aim will be achieved by addressing 4 main objectives

· Review torso shape measurement methods and refine existing methods

· Review feasible methods of body shape measurement using single RGB or RGB-D cameras

· Develop and refine a body shape measurement tool

· Validate the new (low-cost) method against existing (full body scanner) methods.

The project will be centred around 4 studies to address these objectives

1. A review of existing shape methods with scope to adapt current algorithms

2. A scoping review examining state of the art computer vision techniques in shape identification and measurement

3. A pilot study to assess feasibility and efficacy of new shape method measurements

4. A cohort study to validate the new method against current methods – are they measuring the same thing?

Candidate Requirements

Applicants should have a strong undergraduate degree (2.1 or above) and/or a relevant Masters qualification in computer science, computer engineering or a related field, or be able to demonstrate efficacy in this area. Experience of computer vision using RGB or RGB-D cameras, experience with large datasets and related data processing and a desire to work with human participants as part of data collection is advantageous .

Although the project will be based primarily at Sheffield Hallam the student will also complete a period of research at La Trobe in Australia.

How to apply

We strongly recommend you contact the lead academic, Dr Simon Choppin, [Email Address Removed], to discuss your application.

Start date for studentship: February 2023

Interviews are scheduled for: TBC

For information on how to apply and more about the Joint Programme with La Trobe, Australia, please click Global partnership: Joint PhD programme with La Trobe University, Australia | Sheffield Hallam University (shu.ac.uk)

Your application should be emailed to [Email Address Removed] by the closing date of 31st October 2022.

Funding Notes

This is a competition-funded project. We are inviting applications to a number of different projects and are offering up to 3 scholarships which will be awarded to the strongest applicants overall. Further information on the scholarships, including funding and eligibility, is available on our website.
These scholarships are open to Home, EU and International applicants. However, the scholarships pay tuition fees at Home levels only, and students who are liable for the International fee rate will be expected to provide the difference between the Home and International fees from another funding source.

References

1. Després J-P, Lemieux I. Abdominal obesity and metabolic syndrome. Nature. 2006 Dec 13;444(7121):881–7.
2. Han TS, Lean ME. A clinical perspective of obesity, metabolic syndrome and cardiovascular disease. JRSM Cardiovasc Dis. 2016 Mar 21;5:204800401663337.
3. van Namen M, Prendergast L, Peiris CL. Supervised lifestyle intervention for people with metabolic syndrome improves outcomes and reduces individual risk factors of metabolic syndrome: A systematic review and meta-analysis. Metabolism. 2019 Dec;101:153988..
4. M. G. Swainson, A. M. Batterham, C. Tsakirides, Z. H. Rutherford, and K. Hind, “Prediction of whole-body fat percentage and visceral adipose tissue mass from five anthropometric variables,” PLoS ONE, vol. 12, no. 5, May 2017, doi: 10.1371/journal.pone.0177175.
5. M. E. Piché, P. Poirier, I. Lemieux, and J. P. Després, “Overview of Epidemiology and Contribution of Obesity and Body Fat Distribution to Cardiovascular Disease: An Update,” Progress in Cardiovascular Diseases, vol. 61, no. 2. W.B. Saunders, pp. 103–113, Jul. 01, 2018. doi: 10.1016/j.pcad.2018.06.004.
6. World Health Organization., Waist circumference and waist-hip ratio : report of a WHO expert consultation, Geneva, 8-11 December 2008. World Health Organization, 2011.
7. T. Coutinho et al., “Combining body mass index with measures of central obesity in the assessment of mortality in subjects with coronary disease: Role of ‘normal weight central obesity,’” J Am Coll Cardiol, vol. 61, no. 5, pp. 553–560, Feb. 2013, doi: 10.1016/j.jacc.2012.10.035.
8. O. W. A. Wilson, Z. H. Zou, M. Bopp, and C. M. Bopp, “Comparison of obesity classification methods among college students,” Obesity Research and Clinical Practice, vol. 13, no. 5, pp. 430–434, Sep. 2019, doi: 10.1016/j.orcp.2019.09.003.
9. B. K. Ng et al., “Detailed 3-dimensional body shape features predict body composition, blood metabolites, and functional strength: The Shape Up! studies,” American Journal of Clinical Nutrition, vol. 110, no. 6, pp. 1316–1326, 2019, doi: 10.1093/ajcn/nqz218.
10. A. Ruto, M. Lee, and B. Buxton, “Comparing Principal and Independent Modes of Variation in 3D Human Torso Shape Using PCA and ICA,” ICA Research Network International Workshop, vol. 1, no. 4, 2006.
11. Y. Lu, S. McQuade, and J. K. Hahn, “3D Shape-based Body Composition Prediction Model Using Machine Learning,” Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2018-July, pp. 3999–4002, 2018, doi: 10.1109/EMBC.2018.8513261.
12. M. Thelwell, C. Chiu, A. Bullas, J. Hart, J. Wheat, and S. Choppin, “An investigation of how shape-based anthropometry can complement traditional anthropometric techniques,” Scientific Reports (Nature), 2020.
13. M. Thelwell et al., “Modelling of human torso shape variation inferred by geometric morphometrics,” PLOS ONE, vol. 17, no. 3, p. e0265255, Mar. 2022, doi: 10.1371/journal.pone.0265255.
14. S. Choppin, A.Bullas & M. Thelwell “Torso Shape Improves the Prediction of Body Fat Magnitude and Distribution”, International Journal of Environmental Research and Public Health, 2022, [IN REVIEW]