ABSTRACT
Recognizing and understanding surgical high-level tasks from sensor readings is important for surgical workflow analysis. Surgical high-level task recognition is also a challenging task in ubiquitous computing because of the inherent uncertainty of sensor data and the complexity of the operating room environment. In this paper, we present a framework for recognizing high-level tasks from low-level noisy sensor data. Specifically, we present a Markov-based approach for inferring high-level tasks from a set of low-level sensor data. We also propose to clean the noisy sensor data using a Bayesian approach. Preliminary results on a noise-free dataset of ten surgical procedures show that it is possible to recognize surgical high-level tasks with detection accuracies up to 90%. Introducing missed and ghost errors to the sensor data results in a significant decrease of the recognition accuracy. This supports our claim to use a cleaning algorithm before the training step. Finally, we highlight exciting research directions in this area.
