Multiclass Burn Wound Image Classification Using Deep Convolutional Neural Networks

TL;DR

This paper presents a deep learning approach using AlexNet to classify burn wound images into multiple categories, improving accuracy over previous methods for better wound assessment.

Contribution

The study fine-tunes a pre-trained AlexNet model for burn wound classification, achieving over 8% higher accuracy than prior approaches on the same dataset.

Findings

Classification accuracy improved by more than 8%

Effective use of transfer learning for wound image classification

Enhanced reliability in burn wound diagnosis

Abstract

Millions of people are affected by acute and chronic wounds yearly across the world. Continuous wound monitoring is important for wound specialists to allow more accurate diagnosis and optimization of management protocols. Machine Learning-based classification approaches provide optimal care strategies resulting in more reliable outcomes, cost savings, healing time reduction, and improved patient satisfaction. In this study, we use a deep learning-based method to classify burn wound images into two or three different categories based on the wound conditions. A pre-trained deep convolutional neural network, AlexNet, is fine-tuned using a burn wound image dataset and utilized as the classifier. The classifier's performance is evaluated using classification metrics such as accuracy, precision, and recall as well as confusion matrix. A comparison with previous works that used the same dataset showed that our designed classifier improved the classification accuracy by more than 8%.