Our website use cookies to improve and personalize your experience and to display advertisements (if any). Our website may also include cookies from third parties like Google Adsense, Google Analytics, YouTube. By using this website, you consent to the use of cookies. Please click on the button beside to check our Privacy Policy or dismiss this notice with the X in the top-right corner.

Diagnostics of Chronic Wounds

We have conducted a research project into assisting chronic wound management with artificial intelligence. The research has been done jointly with the Alfréd Rényi Institute of Mathematics and the Department of Surgical Research and Techniques of the Medical School of the University of Pécs. An additional 78 larger and smaller health care institutions were also taking part. We have collected 220,000 photographs of chronic wounds with differing etiologies and conditions.

An AI algorithm automatically determining certain parameters of the wound, such as wound diameter, is currently at prototype stage and being tested.

Our main goal is to create an AI algorithm that will provide care recommendation to the attending caregiver. This part of the algorithm is currently in alpha stage – a lab version is operational but not yet sufficiently performant to start testing.

At the system core, there is an artificial intelligence based on deep convolutional neural network, which processes, evaluates and classifies the photos taken on the wounds. In order to train the artificial intelligence system, a lot of sample pictures are required. Due to the regrettable fact that chronic wounds are  widespread, there are many wounds one can take pictures of and these photos can be used with the patient’s consent. Individual wound types can be associated with optimal therapeutic decisions. Showing these pictures and therapeutic decisions to the artificial intelligence, the system learns to identify individual wound types and recommend an optimal therapy. The artificial intelligence makes only recommendations, the specialists should always have the final word!