CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data

Abstract

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.

arXiv commentMaster thesis

References in corpus (12)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Attention U-Net: Learning Where to Look for the Pancreas
• DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Language Modeling with Gated Convolutional Networks
• Comparative Study of CNN and RNN for Natural Language Processing
• Learn To Pay Attention
• A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation
• Attention-Gated Networks for Improving Ultrasound Scan Plane Detection
• Two-Phase Learning for Weakly Supervised Object Localization
• Blending LSTMs into CNNs