Advanced algorithms for surgical gesture classification

A novel gesture binary classification procedure is presented to determine surgical ability. To this aim a sensory glove was employed to track surgical hand movements and sensors data were recorded to be processed by a specific algorithm. The classification task was able to discriminate a gesture made by an expert surgeon with respect to a novice one, thanks to a two steps classification strategy. The first one produced a binary tree of parameters associated to a sensor time function; they were elaborated in the second step by a neural network providing a real output whose magnitude was associated to the surgeon ability. Experimental tests correctly classify all operators in a group.