A simple burn wound severity assessment classifier based on spatial frequency domain imaging (SFDI) and machine learning

Rebecca Rowland, Adrien Ponticorvo, Melissa Baldado, Gordon T. Kennedy, David M. Burmeister, Robert J. Christy, Nicole P. Bernal, Anthony J. Durkin*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

Assessment of burn severity is critical for wound treatment. Spatial frequency domain imaging (SFDI) has been previously used to characterize burns based on the relationships between histology and tissue optical properties. Recently, multispectral and hyperspectral imaging optical features have been combined with machine learning to classify burn severity. Here, we investigated the use of SFDI reflectance data at multiple wavelengths and spatial frequencies, with a support vector machine (SVM), to predict severity in a porcine model of graded burns. Burn severity predictions using SVM were compared to burn grade determined using histology techniques. Results suggest that the combination of spatial frequency data with machine learning models has the potential for accurately predicting burn severity at the 24 hr postburn time point.

Original languageEnglish
Article number1085109
JournalProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10851
DOIs
StatePublished - 2019
Externally publishedYes
EventPhotonics in Dermatology and Plastic Surgery 2019 - San Francisco, United States
Duration: 2 Feb 20193 Feb 2019

Keywords

  • Burns
  • Machine learning
  • Multispectral and hyperspectral imaging
  • Spatial frequency domain imaging
  • Support vector machine
  • Tissue spectroscopy

Fingerprint

Dive into the research topics of 'A simple burn wound severity assessment classifier based on spatial frequency domain imaging (SFDI) and machine learning'. Together they form a unique fingerprint.

Cite this