Paper

Gian Luca Farina * , Carmine Orlandi , Niccolò Gori , Lexa Nescolarde , Henry Lukaski

Abstract: Limitations of body mass index (BMI) as a measure of body fat and the need for practical methods to

estimate body fat reinforce interest in smartphone two-dimensional digital imaging and bioelectrical

impedance analysis (BIA). Compared to dual x-ray absorptiometry (DXA), we determined differences in body

fat mass (FM) estimated with smartphone single lateral standing digital image (SLSDI) and bioimpedance

analysis (BIA) in 188 healthy adults (69 females and 119 males). SLSDI FM estimates were similar to DXA values

but BIA underestimated (p<0.0001) FM. We tested the hypothesis that fluid imbalance, expansion of the

extracellular water (ECW), designated as ECW to intracellular water ratio (ECW/ICW), affects the BIAdependent

differences. With BMI>25 kg/m2, 54 male rugby players, compared to 40 male non-rugby players,

had greater (p<0.001) BMI and fat-free mass but less (p<0.001) FM and ECW/ICW. SLSDI and DXA FM

estimates were not different in both groups; BIA underestimated (p<0.001) FM in the non-rugby men. This

finding is consistent with expansion of ECW in individuals with excess body fat due to increased adipose tissue

mass and its water content. Unlike SLSDI, BIA predictions of FM are affected by altered fluid distribution

associated with increased adipose tissue. These findings establish the validity, practicality, and convenience of

smartphone SLSDI to estimate FM for healthcare providers in clinical and field settings.

Posted Date: 10 August 2023  doi: 10.20944/preprints202308.0812.v1

The present study demonstrates the high precision, concordance, and accuracy of a single, standing lateral 2D digital image (FYO) analyzed using automated machine learning to estimate FM in adults with a wide range of adiposity.

 by Gian Luca Farina 1,*,Carmine Orlandi 2,Henry Lukaski 3 and Lexa Nescolarde 4
1 Medical Center Eubion, 00135 Rome, Italy    2 Medical Faculty, Tor Vergata University, 00133 Rome, Italy
3  Department of Kinesiology and Public Health Education, University of North Dakota, Grand Forks, ND 58202, USA
4 Department of Electronic Engineering, Universitat Politècnica de Catalunya, 08034 Barcelona, Spain
*Author to whom correspondence should be addressed.  Academic Editor: James F. Rusling

Sensors 2022, 22(21), 8365; https://doi.org/10.3390/s22218365 (registering DOI)

Abstract

Background: Obesity is chronic health problem. Screening for the obesity phenotype is limited by the availability of practical methods. Methods: We determined the reproducibility and accuracy of an automated machine-learning method using smartphone camera-enabled capture and analysis of single, two-dimensional (2D) standing lateral digital images to estimate fat mass (FM) compared to dual X-ray absorptiometry (DXA) in females and males. We also report the first model to predict abdominal FM using 2D digital images. Results: Gender-specific 2D estimates of FM were significantly correlated (p < 0.001) with DXA FM values and not different (p > 0.05). Reproducibility of FM estimates was very high (R2 = 0.99) with high concordance (R2 = 0.99) and low absolute pure error (0.114 to 0.116 kg) and percent error (1.3 and 3%). Bland–Altman plots revealed no proportional bias with limits of agreement of 4.9 to −4.3 kg and 3.9 to −4.9 kg for females and males, respectively. A novel 2D model to estimate abdominal (lumbar 2–5) FM produced high correlations (R2 = 0.99) and concordance (R2 = 0.99) compared to DXA abdominal FM values. Conclusions: A smartphone camera trained with machine learning and automated processing of 2D lateral standing digital images is an objective and valid method to estimate FM and, with proof of concept, to determine abdominal FM. It can facilitate practical identification of the obesity phenotype in adults.

Received: 2 October 2022 / Revised: 22 October 2022 / Accepted: 27 October 2022 / Published: 31 October 2022
https://www.mdpi.com/1424-8220/22/21/8365 (This article belongs to the Section Biomedical Sensors)

Gian Luca Farina , Fabrizio Spataro, Antonino De Lorenzo and Henry Lukaski.

PubMed: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5191142/

Abstract:

Personal assessments of body phenotype can enhance success in weight management but are limited by the lack of availability of practical methods. We describe a novel smartphone application of digital photography (DP) and determine its validity to estimate fat mass (FM).

This approach utilizes the percent (%) occupancy of an individual lateral whole-body digital image and regions indicative of adipose accumulation associated with increased risk of cardio-metabolic disease. We measured 117 healthy adults (63 females and 54 males aged 19 to 65 years) with DP and dual X-ray absorptiometry (DXA) and report here the development and validation of this application.

Inter-observer variability of the determination of % occupancy was 0.02%. Predicted and reference FM values were significantly related in females (R2 = 0.949, SEE = 2.83) and males (R2 = 0.907, SEE = 2.71).

Differences between predicted and measured FM values were small (0.02 kg, p = 0.96 and 0.07 kg, p = 0.96) for females and males, respectively. No significant bias was found; limits of agreement ranged from 5.6 to 5.4 kg for females and from 5.6 to 5.7 kg for males. These promising results indicate that DP is a practical and valid method for personal body composition assessments. 

Jordan R. Moon, Sarah E. Tobkin – Ashley A. Walter – Abbie E. Smith – Chris M. Lockwood – Travis W. Beck – Joel T. Cramer – Jeffrey R. Stout

8 th International Symposium on IN VIVO BODY COMPOSITION STUDIES 9 th -12th July 2008, New York, USA

CONCLUSION: The new DiP-based BV equation produced low SEE and TE values and high r 2 values in both the EX and CON groups and accurately tracked BV changes. Therefore, DiP can be considered a valid method for estimating and tracking BV in men and women

Nicola Di Lorenzo, MD, PhD, FACS – Michele Servidio, MD – Laura Di Renzo, PhD – Carmine Orlandi, PhD – Giorgio Coscarella, MD – Achille Gaspari, MD, FACS – Antonino De Lorenzo, MD, PhD

PubMed: https://www.ncbi.nlm.nih.gov/pubmed/16687022

Abstract

BACKGROUND:

The increasing incidence of obesity and the wider acceptance of laparoscopic surgery, have lead to a 10-fold increase in bariatric operations in the last 10 years. Widely used indices of obesity (weight and body mass index – BMI) cannot adequately distinguish between fat mass (FM), represented by the sum of kilograms (kg) of lipid, and fat-free mass (FFM), inclusive of lean (kg of proteins), bone (kg of minerals), glycogen, and total body water (TBW), which are important parameters for clinical and physiological studies.

METHODS:

Anthropometric variables were measured in 19 Caucasian Italian individuals according to standard methods. Body weight (kg) and height (m) were measured, and BMI was calculated as kg/m(2). Body composition was evaluated, with a mean BMI of 25.95+/-5.04 kg/m(2), by dual X-ray absorptiometry (DXA) and by digital image plethysmographic (DIP) acquisition with a digital camera. The clear-colored body of the subjects was automatically converted into a front and lateral red-shaped figure, and then through algorithms the 2 pictures were transformed into a nominal volume; body weight was then divided by the estimated volume, so that the body density could be obtained. DXA was used as a comparison to assess fat mass and fat-free mass. Radiation exposure was <0.6 mSv.

RESULTS:

Significant positive correlation (R= 0.971, P<0.001) was found between data of body composition obtained by DXA and DIP.

CONCLUSIONS:

Body volume assessed using DIP or DXA did not differ. According to this validation study, DIP represents a new promising tool for clinical applications.

Abstract:  A method for determining the fat mass of a subject includes the steps of acquiring an image of the subject through a digital device, and generating a virtual frame that contains at least in part that image. The virtual frame contains the subject, on the basis of its height or of the greater size in the case of animals, to provide an estimation of the content of the fat mass through an algorithm on the basis of at least an indicative index of the area occupied by the subject with respect to the area of the frame in which it is contained at least in part.

Type: Grant
Filed: March 1, 2016
Date of Patent: October 29, 2019
Inventor: Antonio Talluri