A deep learning model for burn depth classification using ultrasound imaging

TL;DR

This paper introduces a deep learning model that accurately classifies burn depths from ultrasound images, potentially aiding clinical assessment with high precision and sensitivity.

Contribution

The study develops a novel deep convolutional neural network with an encoder-decoder architecture for burn depth classification using ultrasound images, demonstrating high accuracy and clinical potential.

Findings

Achieved 99% accuracy in identifying deep-partial thickness burns

High AUC values of 0.99 and 0.95 for ROC and PR curves

Model activates discriminative textural features for classification

Abstract

Identification of burn depth with sufficient accuracy is a challenging problem. This paper presents a deep convolutional neural network to classify burn depth based on altered tissue morphology of burned skin manifested as texture patterns in the ultrasound images. The network first learns a low-dimensional manifold of the unburned skin images using an encoder-decoder architecture that reconstructs it from ultrasound images of burned skin. The encoder is then re-trained to classify burn depths. The encoder-decoder network is trained using a dataset comprised of B-mode ultrasound images of unburned and burned ex vivo porcine skin samples. The classifier is developed using B-mode images of burned in situ skin samples obtained from freshly euthanized postmortem pigs. The performance metrics obtained from 20-fold cross-validation show that the model can identify deep-partial thickness burns, which is the most difficult to diagnose clinically, with 99% accuracy, 98% sensitivity, and 100% specificity. The diagnostic accuracy of the classifier is further illustrated by the high area under the curve values of 0.99 and 0.95, respectively, for the receiver operating characteristic and precision-recall curves. A post hoc explanation indicates that the classifier activates the discriminative textural features in the B-mode images for burn classification. The proposed model has the potential for clinical utility in assisting the clinical assessment of burn depths using a widely available clinical imaging device.