Clinical validation of computer vision and artificial intelligence algorithms for wound measurement and tissue classification in wound care

Abstract

One of the most important challenges in the management and treatment of complex wounds is the observation and measurement of different indicators that can be observed on the wound over time. This article will present the idea of addressing this challenge with the use of images captured on a mobile device. The aim of this work is to evaluate the use of digitization systems in the field of chronic wound management as tools that support the professional in improving patient care and decision making, as well as to use computer vision and artificial intelligence to improve wound assessment. An approach based on visual recognition and a classification system is proposed; visual recognition using superpixel techniques to determine the region of interest of the wound, as well as calculating its area and a classification system based on convolutional networks to classify its tissues. We found that our proposed approach, Visual Computing methods to detect Wound contour and measurement (with a Median Relative Error of 2.907 and inter-rater reliability of 0.98%) and Tissue Classification CNN with excellent results using Resnet50 with 0.85 of accuracy.

Keywords

• Wound measurement
• Assessment
• Tissue classification
• Artificial intelligence
• Computer vision