Locating abnormal heartbeats in ECG segments based on deep weakly supervised learning

Abstract Electrocardiogram (ECG) examination has played a routine and crucial role in many aspects of clinic diagnosis. An auxiliary diagnosis system that can extract effective information from ECG is valuable. In this study, we propose to design a novel multi-instance neural network (MINN) model capable of detecting abnormal ECG segments, meanwhile, locating abnormal heartbeats in them. The model is constructed by convolutional neural network (CNN) and trained under the framework of multiple instance learning. It takes the interaction between the individual heartbeat and whole ECG segment into consideration during the training process, making them constrain each other. MIT-BIH arrhythmia database and CMUH database supported by the First Hospital of China Medical University are used as data resources in this study. 44,332 ECG segments are extracted from both databases to exploit the model. We test our model on ECG segments with various number of heartbeats which are 5, 10, 15 and 20 respectively. The best performance of MINN on detecting ECG segments can achieve a AUC and sensitivity up to 0.9922 and 0.9809, while on locating abnormal heartbeats can achieve a sensitivity up to 0.9473. The test results indicate our system can offer available classification and location messages, having the potential to be applied in the analysis of long-term ECG records.

[1]  Jimeng Sun,et al.  Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review , 2020, ArXiv.

[2]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[3]  Xiaolong Zhai,et al.  Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network , 2018, IEEE Access.

[4]  Brendan J. Frey,et al.  Classifying and segmenting microscopy images with deep multiple instance learning , 2015, Bioinform..

[5]  Muhammad Arif,et al.  Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier , 2012, Journal of Medical Systems.

[6]  Zhuowen Tu,et al.  Multiple clustered instance learning for histopathology cancer image classification, segmentation and clustering , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Yang Hou,et al.  Early detection of ST-segment elevated myocardial infarction by artificial intelligence with 12-lead electrocardiogram. , 2020, International journal of cardiology.

[8]  Xiao Guo,et al.  MetaComp: comprehensive analysis software for comparative meta-omics including comparative metagenomics , 2017, BMC Bioinformatics.

[9]  Metin Nafi Gürcan,et al.  A Multiple Instance Learning Approach toward Optimal Classification of Pathology Slides , 2010, 2010 20th International Conference on Pattern Recognition.

[10]  Ji Feng,et al.  Deep MIML Network , 2017, AAAI.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Ronan Collobert,et al.  From image-level to pixel-level labeling with Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Henggui Zhang,et al.  Detecting atrial fibrillation by deep convolutional neural networks , 2018, Comput. Biol. Medicine.

[14]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[15]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[16]  Mohamed Hammad,et al.  A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication , 2019, Future Gener. Comput. Syst..

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[18]  Joachim M. Buhmann,et al.  Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Paul A. Viola,et al.  Multiple Instance Boosting for Object Detection , 2005, NIPS.

[20]  Yan Xu,et al.  Parallel multiple instance learning for extremely large histopathology image analysis , 2017, BMC Bioinformatics.

[21]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[22]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[23]  Kenneth E. Barner,et al.  A novel application of deep learning for single-lead ECG classification , 2018, Comput. Biol. Medicine.

[24]  Zhipeng Jia,et al.  Constrained Deep Weak Supervision for Histopathology Image Segmentation , 2017, IEEE Transactions on Medical Imaging.

[25]  Ming-Zher Poh,et al.  Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms , 2018, Heart.

[26]  Dayong Wang,et al.  Deep Learning for Identifying Metastatic Breast Cancer , 2016, ArXiv.

[27]  Zhuowen Tu,et al.  Weakly supervised histopathology cancer image segmentation and classification , 2014, Medical Image Anal..

[28]  Jian Wang,et al.  Patient-specific ECG classification by deeper CNN from generic to dedicated , 2018, Neurocomputing.

[29]  U. Rajendra Acharya,et al.  Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats , 2018, Comput. Biol. Medicine.

[30]  U. Rajendra Acharya,et al.  Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals , 2017, Inf. Sci..

[31]  R. Aerts,et al.  East Siberian Arctic inland waters emit mostly contemporary carbon , 2020, Nature Communications.

[32]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[33]  Yixin Chen,et al.  Atrial fibrillation detection by multi-scale convolutional neural networks , 2017, 2017 20th International Conference on Information Fusion (Fusion).

[34]  Thomas B. Schön,et al.  Automatic diagnosis of the 12-lead ECG using a deep neural network , 2020, Nature Communications.

[35]  Trevor Darrell,et al.  Constrained Convolutional Neural Networks for Weakly Supervised Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[36]  Ugur Halici,et al.  A novel deep learning approach for classification of EEG motor imagery signals , 2017, Journal of neural engineering.

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

[38]  Li Sun,et al.  ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection , 2012, IEEE Transactions on Biomedical Engineering.

[39]  Jan Ramon,et al.  Multi instance neural networks , 2000, ICML 2000.

[40]  Tonio Ball,et al.  Deep learning with convolutional neural networks for decoding and visualization of EEG pathology , 2017, 2017 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[41]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[42]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[43]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[44]  Wang Xiangqing,et al.  ECG Signal Classification Algorithm Based on Fusion Features , 2019, Journal of Physics: Conference Series.

[45]  Yan Xu,et al.  Deep learning of feature representation with multiple instance learning for medical image analysis , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).