Machine learning classification of human joint tissue from diffuse reflectance spectroscopy data.

To assess if incorporation of DRS sensing into real-time robotic surgery systems has merit. DRS as a technology is relatively simple, cost-effective and provides a non-contact approach to tissue differentiation. Supervised machine learning analysis of diffuse reflectance spectra was performed to classify human joint tissue that was collected from surgical procedures. We have used supervised machine learning in the classification of a DRS human joint tissue data set and achieved classification accuracy in excess of 99%. Sensitivity for the various classes were; cartilage 99.7%, subchondral 99.2%, meniscus 100% and cancellous 100%. Full wavelength range is required for maximum classification accuracy. The wavelength resolution must be larger than 8nm. A SNR better than 10:1 was required to achieve a classification accuracy greater than 50%. The 800-900nm wavelength range gave the greatest accuracy amongst those investigated DRS is a viable method for differentiating human joint tissue and has the potential to be incorporated into robotic orthopaedic surgery.