Tissue Segmentation for Automatic Chronic Wound Assessment.

Chronic ulcers are usually the result of prolonged pressure on the skin and underlying tissues. The assessment and treatment of wounds require an accurate analysis of their physical characteristics. This is due to the fact that the evolution of the healing allows to evaluate the effectiveness of the treatment. In addition, in most cases, the methods of analysis used nowadays are rudimentary, which leads to errors and the use of invasive and uncomfortable techniques for patients. Important point to determine infection signs and healing process. To do this is important know the quantity of necrotic, sloughy and granulating tissue in wound and their evolution. In this paper we will discuss about Computer Vision and Artificial Intelligence techniques that provide an improvement on tissue segmentation and tissue detection. A mobile application has been developed to acquire the data, enable label assignment before training, and finally display the result of the segmentation. This article discusses about the results of a convolutional neural network as a method of segmentation and how this can improve the clinical practice as a part of wound assessment in a real environment.