Inflammation Assessment of Burn Wound with Deep Learning

Accurate, reliable, and on-time diagnosis, treatment, and follow-up are crucial for effective burn wound management. Currently, the burn injury classification is performed by visual inspection by experienced clinicians and is based on a wound's size and depth. However, clinical inspection presents many shortcomings, including inter-rater variability and poor prognostic accuracy. An automated burn assessment framework could address these challenges and therefore improve burn wound outcomes. This research proposes a convolution neural network (CNN) based deep learning model to assess burn wound. In so doing, the proposed model detects the degree of inflammation of the burn wounds undergoing skin grafting treatment. The dataset used to validate the model was prepared from the 2-D images collected from the Children's Hospital of Michigan/Wayne State University, USA. Experienced burn providers performed the labeling. Based on the ground truth of the labels, the model's accuracy on the test dataset is found to be 0.8750.