Demographic changes and the global epidemics of obesity and diabetes have caused an increase in the number of people suffering from chronic wounds. Wound care can be improved by engaging Innovative imaging techniques within the field of chronic wound diagnostics by predicting and detecting wound infections to accelerate the application of treatments. 

Thus, the infection probability index (IPI) is presented as a novel infection marker based on thermal wound imaging in the present study. Furthermore, the IPI was implemented to automate scoring to improve usability. Visual and thermal image pairs of 60 wounds were obtained for testing the implemented algorithms on clinical data. The suggested method included determining different parameters of the IPI based on medical hypotheses, acquiring data, removing camera distortions using camera calibration, and preprocessing and automating segmentation of the wound to calculate the IPI. 

Wound segmentation is reviewed by user input, while the segmented area can be refined manually. Furthermore, along with the proof of concept, IPIs’ correlation with C-reactive protein (CRP) levels as a clinical infection marker was assessed in this study. 

According to the average CRP levels, the patients were divided into two groups, based on the separation value of an averaged CRP level of 100. The IPIs of the 60 wound images based on automated wound segmentation was calculated with an average runtime of less than a minute. The group having a lower average CRP showed a correlation between IPI and CRP.

Source: J Clin Med. 2021;11(1):169. Published 2021 Dec 29. doi:10.3390/jcm11010169