Analysis of signals, audio and video information

Application of machine learning methods to image analysis of chronic wounds

A. G. Nazarenko^a, E. B. Kleymenova^a, A. I. Molodchenkov^bc, A. S. Ponomarchuk^d, N. P. Gerasimova^a, E. S. Yurchenkova^a, L. P. Yashina<sup>a

a</sup> National Medical Research Center of Traumatology and Orthopedics named after N.N. Priorova, Moscow, Russia
^b Peoples' Friendship University of Russia named after Patrice Lumumba, Moscow, Russia
^c Federal Research Center "Computer Science and Control" of Russian Academy of Sciences, Moscow, Russia
^d National Research University Higher School of Economics, Moscow

Abstract: Neural networks and deep learning algorithms are increasingly used in medicine, including image analysis. In surgery, soft tissue wounds assessment remains challenging but necessary issue to assess the course of healing process and treatment effectiveness. Digital wound images are used for noncontact wound analysis. The paper presents the results of pre-trained network models (AlexNet, ResNet50, ResNet152, VGG16) used to classify pressure ulcer images as examples of chronic wounds. The Segment Anything Model (SAM) demonstrated an accuracy of 86.46% in solving the problem of segmenting the edges of a wound defect and tissue types within it. The results can be used to create an expert system for analyzing soft tissue wound images.

Keywords: artificial intelligence, machine learning, image recognition, pressure ulcers, wounds.

DOI: 10.14357/20718594250109

Bibliographic databases:

•