Application of machine learning methods to image analysis of chronic wounds

Authors

Molodchenkov A. Kleimyonova E. Yashina L.

Annotation

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.

External links

DOI: 10.14357/20718594250109

Download PDF from the Russian Centre for Science Information (subscription required): https://journals.rcsi.science/2071-8594/article/view/293506

eLibrary: https://elibrary.ru/item.asp?id=80493705

Math-Net.Ru: https://www.mathnet.ru/eng/iipr621

Reference link

Nazarenko A. G., Kleymenova E. B., Molodchenkov A. I., Ponomarchuk A. S., Gerasimova N. P., Yurchenkova E. S., Yashina L. P. Application of machine learning methods to image analysis of chronic wounds // Artificial Intelligence and Decision Making, 2025, Issue 1, pp. 103–114.