A Hybrid Approach for Tissue Recognition on Wound Images

Pressure ulcer is a clinical pathology of localized damage to the skin and underlying tissue caused by pressure, shear o friction. Diagnosis, treatment and care of pressure ulcers involve high costs for sanitary systems. Accurate wound evaluation is a critical task for optimizing the effectiveness of treatments and care. Clinicians usually evaluate each pressure ulcer by visual inspection of the damaged tissues, which is an imprecise manner of assessing the wound state. Current computer vision approaches do not offer a global solution to this particular problem. In this article, a hybrid approach based on neural networks and Bayesian classifiers is used in the designing of a computational system for automatic tissue identification on wound images. A mean shift procedure and a region-growing strategy are implemented for effective region segmentation. Color and texture features are extracted from the segmented regions. A set of k multi-layer perceptrons are trained with inputs consisting of color and texture patterns, and outputs consisting of categorical tissue classes which are determined by clinical experts. This training procedure is driven by a k-fold cross-validation method. Finally, a Bayesian committee machine is formed by training a Bayesian classifier to combine the classifications of the k neural networks. Our outcomes show high performance scores of a two-stage cascade approach for tissue identification.