Automatic burn area identification in color images

This papers presents the use of color imaging as a starting point of burn wound evaluation, by the discrimination between healthy skin and burn wound. The skin/burn area identification is performed pixel-wise, according to the properties of an entire encompassing patch. The classification is learned under a supervised scenario, according to a ground truth defined by specialist surgeons from a large pediatric case database, by a deep learned convolutional neural network. The database is extensive and was recorded over several months in real, hospital conditions The proposed approach achieves an overall performance comparable to the literature-reported average performance of a specialist surgeon.