Automated Robust Interpretation of Intraoperative Electrophysiological Signals – A Bayesian Deep Learning Approach

Abstract

Abstract Intraoperative neurophysiological monitoring (IONM) is an essential tool during numerous surgical interventions to assess and monitor the functional integrity of neural structures at risk. A reliable signal interpretation is of importance to support medical staff by reducing manual evaluation. Deep learning (DL) techniques proved to be a robust tool for the analysis of neurophysiological data. The large amount of required manually labeled data as well as the lack of interpretability of the results however often limit the use of DL in medical scenarios. A possible way to tackle these obstacles is the utilization of Bayesian deep learning (BDL) methods. The modelling of uncertainties in the network parameters and the thereby possible quantification of predictive uncertainties allows both the identification of potential erroneous predictions as well as the targeted selection of informative signals in the context of active learning. To evaluate the applicability of BDL for the analysis of electrophysiological data as well as to increase the training efficiency by active learning, we implemented a multi-task Bayesian Convolutional Neural Network (BCNN) for the simultaneous classification of action potentials and the assessment of relevant signal characteristics (latency, maximum, minimum). We compare the results for electromyographical signals (EMG), containing in total approximately twelve thousand signals from 34 patients, with both a traditional non-Bayesian single-task and multi-task CNN. For all models, including the BCNN, we could achieve similar performances with detection rates over 97% accuracy. Further, we could improve training efficiency of the BCNN using pool-based active learning and therefore significantly reduce the required amount of manual labeling. The evaluated predictive uncertainties of the BCNN prove useful both for the efficient selection of informative signals in the context of active learning as well as the interpretation of the predictive posterior distribution and therefore trustworthiness of the classifications.