[Skip to Navigation]
Sign In
Views 614
Citations 0
Original Investigation
November 24, 2021

Practical Computer Vision Application to Compute Total Body Surface Area Burn: Reappraising a Fundamental Burn Injury Formula in the Modern Era

Author Affiliations
  • 1Department of Surgery, Stanford University, Stanford, California
  • 2Surgeons Writing About Trauma, Stanford University, Stanford, California
  • 3Department of Computer Science, Stanford University, Stanford, California
  • 4School of Engineering, Stanford University, Stanford, California
  • 5School of Medicine, Stanford University, Stanford, California
JAMA Surg. Published online November 24, 2021. doi:10.1001/jamasurg.2021.5848
Key Points

Question  Can computer vision algorithms facilitate accurate percent total body surface area (%TBSA) burn computation across the wide body habitus spectrum of the modern population?

Findings  In this cohort study, 3-dimensional image segmentation of 3047 adult laser body scans were integrated into a mobile application that computes %TBSA burn based on exact burn injury pattern, sex, and body habitus. There is wide individual variability in how much each body region contributes to %TBSA, and the tool developed in this study reflects measured body surface areas of adults across the wide body habitus spectrum of the modern population.

Meaning  An intuitive, accurate, and practical mobile application may be an improvement over existing one-size-fits-all models for computing %TBSA burn, a foundational estimate for burn injury management.

Abstract

Importance  Critical burn management decisions rely on accurate percent total body surface area (%TBSA) burn estimation. Existing %TBSA burn estimation models (eg, Lund-Browder chart and rule of nines) were derived from a linear formula and a limited number of individuals a century ago and do not reflect the range of body habitus of the modern population.

Objective  To develop a practical %TBSA burn estimation tool that accounts for exact burn injury pattern, sex, and body habitus.

Design, Setting, and Participants  This population-based cohort study evaluated the efficacy of a computer vision algorithm application in processing an adult laser body scan data set. High-resolution surface anthropometry laser body scans of 3047 North American and European adults aged 18 to 65 years from the Civilian American and European Surface Anthropometry Resource data set (1998-2001) were included. Of these, 1517 participants (49.8%) were male. Race and ethnicity data were not available for analysis. Analyses were conducted in 2020.

Main Outcomes and Measures  The contributory %TBSA for 18 body regions in each individual. Mobile application for real-time %TBSA burn computation based on sex, habitus, and exact burn injury pattern.

Results  Of the 3047 individuals aged 18 to 65 years for whom body scans were available, 1517 (49.8%) were male. Wide individual variability was found in the extent to which major body regions contributed to %TBSA, especially in the torso and legs. Anterior torso %TBSA increased with increasing body habitus (mean [SD], 15.1 [0.9] to 19.1 [2.0] for male individuals; 15.1 [0.8] to 18.0 [1.7] for female individuals). This increase was attributable to increase in abdomen %TBSA (mean [SD], 5.3 [0.7] to 8.7 [1.8]) among male individuals and increase in abdomen (mean [SD], 4.6 [0.6] to 6.8 [1.7]) and pelvis (mean [SD], 1.5 [0.2] to 2.9 [0.9]) %TBSAs among female individuals. For most body regions, Lund-Browder chart and rule of nines estimates fell outside the population’s measured interquartile ranges. The mobile application tested in this study, Burn Area, facilitated accurate %TBSA burn computation based on exact burn injury pattern for 10 sex and body habitus-specific models.

Conclusions and Relevance  Computer vision algorithm application to a large laser body scan data set may provide a practical tool that facilitates accurate %TBSA burn computation in the modern era.

Add or change institution
Limit 200 characters
Limit 25 characters
Conflicts of Interest Disclosure

Identify all potential conflicts of interest that might be relevant to your comment.

Conflicts of interest comprise financial interests, activities, and relationships within the past 3 years including but not limited to employment, affiliation, grants or funding, consultancies, honoraria or payment, speaker's bureaus, stock ownership or options, expert testimony, royalties, donation of medical equipment, or patents planned, pending, or issued.

Err on the side of full disclosure.

If you have no conflicts of interest, check "No potential conflicts of interest" in the box below. The information will be posted with your response.

Not all submitted comments are published. Please see our commenting policy for details.

Limit 140 characters
Limit 3600 characters or approximately 600 words
    ×