Application of physics-based deep learning models for classification of burn injuries and prediction of the wound healing outcomes using the terahertz PHASR scanner

Zachery B. Harris; Mahmoud E. Khani; Omar B. Osman; M. Hassan Arbab

doi:10.1117/12.3003891

13 March 2024 Application of physics-based deep learning models for classification of burn injuries and prediction of the wound healing outcomes using the terahertz PHASR scanner

Zachery B. Harris, Mahmoud E. Khani, Omar B. Osman, M. Hassan Arbab

Author Affiliations +

Proceedings Volume PC12831, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXII; PC1283107 (2024) https://doi.org/10.1117/12.3003891
Event: SPIE BiOS, 2024, San Francisco, California, United States

Abstract

Traditional diagnostic methods for burn wounds have remained inaccurate.We have recently demonstrated that terahertz (THz) spectroscopic imaging can assess wound severity and predict healing outcome with high accuracy using our Portable HAndheld Spectral Reflection (PHASR) Scanners, which provide fast full-spectroscopic imaging. We will describe recent work exploring different physics-based machine learning methods to classify wounds using THz spectral data. THz images captured 1-hour post-burn achieve an accuracy of 94.7% in predicting the wound healing outcome by 28 days. A reduced-dimensionality double-Debye model describes the refractive index of the tissue over the entire spectra using only five empirical parameters. A neural network based on this model still achieved 88% healing outcome prediction accuracy. Finally, we will discuss plans to translate this technology to clinical trials.

Conference Presentation

Citation Download Citation

Zachery B. Harris, Mahmoud E. Khani, Omar B. Osman, and M. Hassan Arbab "Application of physics-based deep learning models for classification of burn injuries and prediction of the wound healing outcomes using the terahertz PHASR scanner", Proc. SPIE PC12831, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXII, PC1283107 (13 March 2024); https://doi.org/10.1117/12.3003891

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Injuries

Scanners

Wound healing

Terahertz radiation

Reflection

Deep learning

Imaging spectroscopy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years