17 March 2023Comparative evaluation of conventional color imaging and hyperspectral imaging data as inputs to machine learning algorithms for classifying burn severity
Samagra Pandey,1 Gordon T. Kennedy,1 Rebecca A. Rowlandhttps://orcid.org/0000-0002-8913-9599,1 Victor C. Joe,2 Theresa L. Chin,2 Robert J. Christy,3 David M. Burmeister,4 Robert H. Wilson,2 Anthony J Durkin5
1Beckman Laser Institute and Medical Clinic (United States) 2Univ. of California, Irvine (United States) 3The Univ. of Texas Health Science Ctr. at San Antonio (United States) 4Uniformed Services Univ. of the Health Sciences (United States) 5Beckman Laser Institute and Medical Clinic, Univ. of California, Irvine (United States)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Accurately classifying burn severity is crucial to inform proper treatment. Here, we quantitatively compare the efficacy of machine learning (ML) burn classification algorithms using multispectral imaging versus conventional digital color imaging data as inputs. We imaged 80 porcine burns that underwent biopsy and histology for ground truth categorization into “skin graft needed” versus “no graft needed” groups. The accuracy of our ML algorithm with a transfer learning architecture was 97.5% for the multispectral model, 57.5% for the digital-color model, and 57.5% for the multispectral+digital-color model. This result strongly supports the use of multispectral imaging over digital-color imaging for burn classification.
Samagra Pandey,Gordon T. Kennedy,Rebecca A. Rowland,Victor C. Joe,Theresa L. Chin,Robert J. Christy,David M. Burmeister,Robert H. Wilson, andAnthony J Durkin
"Comparative evaluation of conventional color imaging and hyperspectral imaging data as inputs to machine learning algorithms for classifying burn severity", Proc. SPIE PC12352, Photonics in Dermatology and Plastic Surgery 2023, PC1235207 (17 March 2023); https://doi.org/10.1117/12.2664961
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Samagra Pandey, Gordon T. Kennedy, Rebecca A. Rowland, Victor C. Joe, Theresa L. Chin, Robert J. Christy, David M. Burmeister, Robert H. Wilson, Anthony J Durkin, "Comparative evaluation of conventional color imaging and hyperspectral imaging data as inputs to machine learning algorithms for classifying burn severity," Proc. SPIE PC12352, Photonics in Dermatology and Plastic Surgery 2023, PC1235207 (17 March 2023); https://doi.org/10.1117/12.2664961