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

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.

[1]  Wenpeng Yin,et al.  Comparative Study of CNN and RNN for Natural Language Processing , 2017, ArXiv.

[2]  Qiao Li,et al.  AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017 , 2017, 2017 Computing in Cardiology (CinC).

[3]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Sally Hopewell,et al.  Atrial fibrillation and risks of cardiovascular disease, renal disease, and death: systematic review and meta-analysis , 2016, British Medical Journal.

[5]  Benjamin Schrauwen,et al.  Training and Analysing Deep Recurrent Neural Networks , 2013, NIPS.

[6]  Michael Tschannen,et al.  Convolutional recurrent neural networks for electrocardiogram classification , 2017, 2017 Computing in Cardiology (CinC).

[7]  Julien Oster,et al.  Rhythm and quality classification from short ECGs recorded using a mobile device , 2017, 2017 Computing in Cardiology (CinC).

[8]  Joan Lasenby,et al.  What does an LSTM look for in classifying heartbeats , 2017 .

[9]  Nikos Komodakis,et al.  Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer , 2016, ICLR.

[10]  Stefan Wermter,et al.  Gesture Recognition with a Convolutional Long Short-Term Memory Recurrent Neural Network , 2016, ESANN.

[11]  Yue Chen,et al.  The Study of Electrocardiograph Based on Radial Basis Function Neural Network , 2010, 2010 Third International Symposium on Intelligent Information Technology and Security Informatics.

[12]  Yann Dauphin,et al.  Language Modeling with Gated Convolutional Networks , 2016, ICML.

[13]  Tara N. Sainath,et al.  Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Saeed Babaeizadeh,et al.  Densely connected convolutional networks and signal quality analysis to detect atrial fibrillation using short single-lead ECG recordings , 2017, 2017 Computing in Cardiology (CinC).

[15]  Matthew Richardson,et al.  Blending LSTMs into CNNs , 2015, ICLR 2016.

[16]  Philip H. S. Torr,et al.  Learn To Pay Attention , 2018, ICLR.

[17]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[18]  Shuicheng Yan,et al.  A survey on deep learning-based fine-grained object classification and semantic segmentation , 2017, International Journal of Automation and Computing.

[19]  Dahun Kim,et al.  Two-Phase Learning for Weakly Supervised Object Localization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[21]  Gari D Clifford,et al.  Comparison of three artificial models of the magnetohydrodynamic effect on the electrocardiogram , 2015, Computer methods in biomechanics and biomedical engineering.

[22]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[23]  Masun Nabhan Homsi,et al.  Cardiac arrhythmia detection from ECG combining convolutional and long short-term memory networks , 2017, 2017 Computing in Cardiology (CinC).

[24]  Denis Turdakov,et al.  Comparison of neural network architectures for sentiment analysis of Russian tweets , 2016 .

[25]  Ki H. Chon,et al.  Atrial Fibrillation Detection Using an iPhone 4S , 2013, IEEE Transactions on Biomedical Engineering.

[26]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[27]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[28]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[29]  Liang-Yu Shyu,et al.  Using wavelet transform and fuzzy neural network for VPC detection from the holter ECG , 2004, IEEE Transactions on Biomedical Engineering.

[30]  Liang Chen,et al.  Attention-Gated Networks for Improving Ultrasound Scan Plane Detection , 2018, MICCAI 2018.

[31]  Andrea Vedaldi,et al.  Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[32]  Chao Wu,et al.  DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[33]  Aggelos K. Katsaggelos,et al.  Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier , 2017, 2017 Computing in Cardiology (CinC).

[34]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[35]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[36]  Manisha Jangra,et al.  Recent trends in arrhythmia beat detection: A review , 2016 .

[37]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[38]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[39]  李永军,et al.  Atrial Fibrillation , 1999 .

[40]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[41]  Yakoub Bazi,et al.  Convolutional Neural Networks for Electrocardiogram Classification , 2018, Journal of Medical and Biological Engineering.

[42]  Wei Xu,et al.  Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[43]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[44]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[45]  Gang Chen,et al.  A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation , 2016, ArXiv.

[46]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[47]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[48]  Rahul Wadke,et al.  Atrial fibrillation. , 2022, Disease-a-month : DM.

[49]  Chandan Chakraborty,et al.  Application of principal component analysis to ECG signals for automated diagnosis of cardiac health , 2012, Expert Syst. Appl..

[50]  Loïc Le Folgoc,et al.  Attention U-Net: Learning Where to Look for the Pancreas , 2018, ArXiv.

[51]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[52]  Paulo Félix,et al.  Arrhythmia classification from the abductive interpretation of short single-lead ECG records , 2017, 2017 Computing in Cardiology (CinC).