Real-time tissue differentiation based on optical emission spectroscopy for guided electrosurgical tumor resection

Complete surgical removal of cancer tissue with effective preservation of healthy tissue is one of the most important challenges in modern oncology. We present a method for real-time, in situ differentiation of tissue based on optical emission spectroscopy (OES) performed during electrosurgery not requiring any biomarkers, additional light sources or other excitation processes. The analysis of the optical emission spectra, enables the differentiation of healthy and tumorous tissue. By using multi-class support vector machine (SVM) algorithms, distinguishing between tumor types also seems to be possible. Due to its fast reaction time (0.05s) the method can be used for real-time navigation helping the surgeon achieve complete resection. The system's easy realization has been proven by successful integration in a commercial electro surgical unit (ESU). In a first step the method was verified by using ex vivo tissue samples. The histological analysis confirmed, 95% of correctly classified tissue types.