The use of mobile thermal imaging and machine learning technology for the detection of early surgical site infections

Abstract

BackgroundSurgical Site Infections (SSI) yield subtle, early signs that are not readily identifiable. This study sought to develop a machine learning algorithm that could identify early SSIs based on thermal images. MethodsImages were taken of surgical incisions on 193 patients who underwent a variety of surgical procedures. Two neural network models were generated to detect SSIs, one using RGB images, and one incorporating thermal images. Accuracy and Jaccard Index were the primary metrics by which models were evaluated. ResultsOnly 5 patients in our cohort developed SSIs (2.8%). Models were instead generated to demarcate the wound site. The models had 89–92% accuracy in predicting pixel class. The Jaccard indices for the RGB and RGB ​+ ​Thermal models were 66% and 64%, respectively. ConclusionsAlthough the low infection rate precluded the ability of our models to identify surgical site infections, we were able to generate two models to successfully segment wounds. This proof-of-concept study demonstrates that computer vision has the potential to support future surgical applications.