CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
This work addresses the problem of automated ECG diagnosis for clinicians by enhancing classification accuracy and interpretability, though it is incremental as it builds on existing architectures.
The study tackled ECG rhythm classification by combining CNNs and LSTMs into ConvLSTM networks and integrating attention mechanisms to capture morphological and temporal features, achieving improved performance on the PhysioNet CinC 2017 dataset with an 8-fold cross-validation.
For the weakly supervised task of electrocardiogram (ECG) rhythm classification, convolutional neural networks (CNNs) and long short-term memory (LSTM) networks are two increasingly popular classification models. This work investigates whether a combination of both architectures to so-called convolutional long short-term memory (ConvLSTM) networks can improve classification performances by explicitly capturing morphological as well as temporal features of raw ECG records. In addition, various attention mechanisms are studied to localize and visualize record sections of abnormal morphology and irregular rhythm. The resulting saliency maps are supposed to not only allow for a better network understanding but to also improve clinicians' acceptance of automatic diagnosis in order to avoid the technique being labeled as a black box. In further experiments, attention mechanisms are actively incorporated into the training process by learning a few additional attention gating parameters in a CNN model. An 8-fold cross validation is finally carried out on the PhysioNet Computing in Cardiology (CinC) challenge 2017 to compare the performances of standard CNN models, ConvLSTMs, and attention gated CNNs.