The Burn Medical Assistant: Developing Machine Learning Algorithms to Aid in the Estimation of Burn Wound Size

Abstract

We will test the hypothesis that a computer machine learning algorithm can analyze and classify burn injures using multispectral imaging within 5% of an expert clinician through a series of steps. First, we will develop a model to map images of burn wounds captured from a portable multispectral camera to a standard Lund-Browder burn wound diagram. We will then have burn wound experts estimate the burn wound size using an enhanced burn wound diagram. The mappings made by burn wound experts will then be compared to automated measurements. Finally, through the use of machine learning (ML), we will build models from these multispectral images and expert burn wound mapping to create a predictive model of burn wound size and depth that will approximate an expert's opinion to within 5%.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 2017
Accession Number
AD1048286

Entities

People

  • Christopher Argenta
  • Gregory Rule
  • Jeremy Pamplin
  • Maria Serio-melvin

Tags

Communities of Interest

  • Autonomy
  • Biomedical

DTIC Thesaurus Topics

  • Acquisition
  • Algorithms
  • Application Software
  • Burns
  • Cameras
  • Combat Casualty Care
  • Computer Vision
  • Computers
  • Data Acquisition
  • Data Sets
  • Detection
  • Health Services
  • Human Body
  • Learning
  • Machine Learning
  • Predictive Modeling
  • Standards

Fields of Study

  • Medicine

Readers

  • Artificial Intelligence
  • Neural Network Machine Learning.
  • Trauma Surgery or Emergency Medicine.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks