Tensor Convolutional Sparse Coding with Low-Rank activations, an application to EEG analysis
This work addresses the challenge of noisy EEG signal analysis for medical applications like studying consciousness during anesthesia, representing an incremental improvement by adapting existing methods to tensor-specific structures.
The paper tackles the problem of analyzing EEG spectrograms during general anesthesia by introducing a new convolutional sparse coding model called K-CSC, which leverages low-rank tensor structures to extract relevant encodings; results show that their method, TC-FISTA, is robust to noise and yields accurate, sparse, and interpretable encodings on both synthetic and real EEG data.
Recently, there has been growing interest in the analysis of spectrograms of ElectroEncephaloGram (EEG), particularly to study the neural correlates of (un)-consciousness during General Anesthesia (GA). Indeed, it has been shown that order three tensors (channels x frequencies x times) are a natural and useful representation of these signals. However this encoding entails significant difficulties, especially for convolutional sparse coding (CSC) as existing methods do not take advantage of the particularities of tensor representation, such as rank structures, and are vulnerable to the high level of noise and perturbations that are inherent to EEG during medical acts. To address this issue, in this paper we introduce a new CSC model, named Kruskal CSC (K-CSC), that uses the Kruskal decomposition of the activation tensors to leverage the intrinsic low rank nature of these representations in order to extract relevant and interpretable encodings. Our main contribution, TC-FISTA, uses multiple tools to efficiently solve the resulting optimization problem despite the increasing complexity induced by the tensor representation. We then evaluate TC-FISTA on both synthetic dataset and real EEG recorded during GA. The results show that TC-FISTA is robust to noise and perturbations, resulting in accurate, sparse and interpretable encoding of the signals.