Review : Wound Classification using Ensemble Deep CNN

Wounds are a challenge to healthcare systems around the world and affect many people’s lives annually. Wound classification is a key step in wound diagnosis that would help clinicians to identify an optimal treatment procedure. Hence, having a high-performance classifier assists the specialists in the field to classify the wounds with less financial and time costs. The main difficulties in treating chronic wounds are overcoming the causes of delayed healing, which are essential elements of a thorough approach to wound care. After four weeks of normal care, wounds that don’t heal enough should be evaluated for underlying pathology and the need for advanced therapeutic drugs. A Machine Learning based wound classification methods have been proposed in the literature. The proposed system classifies the given image according to the trained data set. We have trained a model for five generalized wound classes namely Burn, Hematoma, Abscessed/infectious, Abrasion and Incision/Cut/ puncture Wound. This model will classify the given input image into its corresponding class in ease. Certain management procedures will also be provided for assisting the wound care. In future where robotic treatment are to come, such models will be of great importance for practical implementations.