A research paper by Anton Kontunen was published in IEEE Sensors Journal! The article presents evidence for real time tissue identification from diathermy smoke by DMS.
The study presents an integrated sensor system that can measure a surgical smoke sample in seconds and relay the information of the tissue type to the user in near real time in simulated surgical use. Porcine adipose and muscle tissues were used to validate the system, with cross-validated linear discriminant analysis model yielding a 93.1 % classification accuracy (CA) on 1059 samples. A convolutional neural network model was used to classify the same dataset, resulting in a CA of 93.2 %.
The results indicate that real time tissue identification is possible from surgical smoke produced in freehand surgery. This could offer and improvement to intraoperative surgical margin assessment.
Read more on IEEE