Detection of bone infections using Vis-NIR and SWIR hyperspectral imaging coupled with machine learning

Area of Science:

• Orthopaedic Surgery
• Medical Imaging
• Microbiology

Background:

• Bone infections pose significant diagnostic and therapeutic challenges in orthopaedic surgery.
• Current diagnostic methods, like tissue cultures, are slow and lack sensitivity, delaying critical clinical decisions.
• Rapid and accurate detection of bone infections is crucial for effective treatment and patient outcomes.

Purpose of the Study:

• To investigate the efficacy of hyperspectral imaging (HSI) in the visible and near-infrared (Vis-NIR) and short-wave infrared (SWIR) spectral ranges for rapid bone infection detection.
• To evaluate machine learning algorithms for analyzing spectral data to differentiate infected from uninfected bone samples.
• To assess HSI's potential as a real-time, label-free tool for intraoperative bone infection diagnosis.

Main Methods:

• Ex vivo human bone samples were used to establish an in vitro biofilm model with Staphylococcus aureus and Staphylococcus epidermidis.
• Hyperspectral imaging (HSI) was performed in the Vis-NIR and SWIR spectral ranges.
• Spectral data were analyzed using machine learning algorithms, including k-nearest neighbors (kNN), support vector machine (SVM), partial least squares discriminant analysis (PLS-DA), and soft independent modeling of class analogy (SIMCA).

Main Results:

• Vis-NIR-HSI models demonstrated superior performance compared to SWIR-based classification.
• Classification accuracies of up to 99.58% were achieved in distinguishing inoculated from uninoculated human bone samples.
• The Vis-NIR-HSI approach enabled accurate differentiation of bacterial species.

Conclusions:

• Vis-NIR-HSI shows significant potential as a real-time, label-free intraoperative tool for detecting bone infections.
• This technology can bridge the gap between preoperative imaging and delayed microbiological results.
• The findings support immediate surgical decision-making in cases of suspected bone infection.