FusionAtt: Deep Fusional Attention Networks for Multi-Channel Biomedical Signals

Abstract

Recently, pervasive sensing technologies have been widely applied to comprehensive patient monitoring in order to improve clinical treatment. Various types of biomedical signals collected by different sensing channels provide different aspects of patient health information. However, due to the uncertainty and variability in clinical observation, not all the channels are relevant and important to the target task. Thus, in order to extract informative representations from multi-channel biosignals, channel awareness has become a key enabler for deep learning in biosignal processing and has attracted increasing research interest in health informatics. Towards this end, we propose FusionAtt—a deep fusional attention network that can learn channel-aware representations of multi-channel biosignals, while preserving complex correlations among all the channels. FusionAtt is able to dynamically quantify the importance of each biomedical channel, and relies on more informative ones to enhance feature representation in an end-to-end manner. We empirically evaluated FusionAtt in two clinical tasks: multi-channel seizure detection and multivariate sleep stage classification. Experimental results showed that FusionAtt consistently outperformed the state-of-the-art models in four different evaluation measurements, demonstrating the effectiveness of the proposed fusional attention mechanism.

Hybrid Network with Attention Mechanism for Detection and Location of Myocardial Infarction Based on 12-Lead Electrocardiogram Signals

“…Recently, attention mechanism has been popular in clinical diagnosis. Deep fusional attention network was adopted to extract elaborate features from biological signals in seizure detection and sleep stage classification [16]. In MI diagnosis, the heartbeat-attention mechanism was introduced to automatically weight the difference between unlabeled heartbeats [22].…”

“…In recent decades, deep learning methods, including convolutional neural network (CNN), gated recurrent unit (GRU), attention mechanism, and autoencoder, have been widely and superbly applied to analyze biomedical signals [14][15][16]. Instead of separate feature extraction and classification processes, deep learning architectures automatically extract critical features required for classification from vast samples [17].…”

Notable Papers and Trends from 2019 in Sensors, Signals, and Imaging Informatics

“…The authors propose a CNN-based approach which directly fuses information from multiple physiological signals for estimating heartbeat locations without the need for any intermediate detection. Another example is a deep fusional attention network by Ye et al, FusionAtt [8], which uses a unified fusional attention neural network combined with a multi-view convolutional encoder to learn channel-aware representations of multi-channel biosignals. FusionAtt outperformed baseline approaches on two clinical tasks, seizure detection using data from 23-channel scalp electroencephalogram and sleep stage classification using data from 14-channel polysomnography.…”

Comparison of Attention-based Deep LearningModels for EEG Classification

“…In [20], ChannelAtt has been designed to jointly learn both multi-view data representations from a multi-channel EEG dataset and their contribution scores to dynamically identify irrelavant channels in a seizure detection problem. Fusion-Att [21], a deep fusional attention network, can learn channel-aware representations of multi-channel biosignals, and dynamically quantify the importance of each channel. Cho et al [22] and Ma et al [23] introduced AttnSense, a framework to combine attention mechanisms with CNNs and GRU in order to capture the dependencies of the sensed signals in both the spatial and the time domains.…”