From ECG signals to images: a transformation based approach for deep learning (original) (raw)
Related papers
2020
Background: Electrocardiogram (ECG) is a method of recording the electrical activity of the heart and provides a diagnostic mean for heart-related diseases. An arrhythmia is any irregularity of heartbeat that causes an abnormality in one's heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG signal is not sufficient for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to developed computer-aided diagnosis (CAD) systems to automatically identify arrhythmias. Methods: This paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The signals are obtained from MIT-BIH arrhythmia database and are categorized according to five arrhythmia types. The proposed approach identifies arrhythmia classes by using Convolutional Neural Network (CNN) architecture trained by twodimensional (2D) ECG beat images. CNN architecture is selected due to high image recognition performance. ECG signals are segmented into heartbeats, then each heartbeat is transformed into a 2D grayscale image. The heartbeat images are used as input for the CNN. Results: The proposed CNN model is compared to other common CNN architectures such as LeNet and ResNet-50 to evaluate the performance of our study. Overall, the proposed study achieved 99.7% test accuracy in the classification of five different ECG arrhythmias. Conclusions: Testing results demonstrate that CNN trained by ECG image representations provide outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Hence, the proposed approach provides a robust method for the classification of ECG arrhythmias.
Cardiac arrhythmia detection using deep learning
Procedia Computer Science, 2017
An electrocardiogram (ECG) is an important diagnostic tool for the assessment of cardiac arrhythmias in clinical routine. In this study, a deep learning framework previously trained on a general image data set is transferred to carry out automatic ECG arrhythmia diagnostics by classifying patient ECG's into corresponding cardiac conditions. Transferred deep convolutional neural network (namely AlexNet) is used as a feature extractor and the extracted features are fed into a simple back propagation neural network to carry out the final classification. Three different conditions of ECG waveform are selected from MIT-BIH arrhythmia database to evaluate the proposed framework. Main focus of this study is to implement a simple, reliable and easily applicable deep learning technique for the classification of the selected three different cardiac conditions. Obtained results demonstrated that the transferred deep learning feature extractor cascaded with a conventional back propagation neural network were able to obtain very high performance rates. Highest obtained correct recognition rate is 98.51% while obtaining testing accuracy around 92%. Based on these results, transferred deep learning proved to be an efficient automatic cardiac arrhythmia detection method while eliminating the burden of training a deep convolutional neural network from scratch providing an easily applicable technique.
ECG Classification for Detecting ECG Arrhythmia Empowered with Deep Learning Approaches
Computational Intelligence and Neuroscience
According to the World Health Organization (WHO) report, heart disease is spreading throughout the world very rapidly and the situation is becoming alarming in people aged 40 or above (Xu, 2020). Different methods and procedures are adopted to detect and diagnose heart abnormalities. Data scientists are working on finding the different methods with the required accuracy (Strodthoff et al., 2021). Electrocardiogram (ECG) is the procedure to find the heart condition in the waveform. For ages, the machine learning techniques, which are feature based, played a vital role in the medical sciences and centralized the data in cloud computing and having access throughout the world. Furthermore, deep learning or transfer learning widens the vision and introduces different transfer learning methods to ensure accuracy and time management to detect the ECG in a better way in comparison to the previous and machine learning methods. Hence, it is said that transfer learning has turned world researc...
Deep Learning Approach Based on Transfer Learning with Different Classifiers for Ecg Diagnosis
International journal of intelligent computing and information sciences, 2022
Heart diseases are one of the main reasons that cause human death. The early-stage detection of heart diseases can prevent irreversible heart muscle damage or heart failure. Electrocardiogram (ECG) is one of the main heart signals that can be useful in early diagnosis because of its obvious peaks and segments. This paper focuses on using a methodology depending on deep learning for the diagnosis of the electrocardiogram records into normal (N), Supraventricular arrhythmia (SV), ST-segment changes (ST), and myocardial infarction (MYC) conditions. The continuous wavelet transform (CWT) converts the ECG signals to the time-frequency domain to compute the scalogram of the ECG signals and for the conversion of ECG signal from one dimension signal to a two-dimension image. In addition to this, a pertained model using transfer learning is applied based on Resnet50. Moreover, three main classifiers are verified to estimate the accuracy of the proposed system which are based on the Softmax, Random Forest (RF), and XGBoost classifier. An experiment is applied for the diagnosis of four main kinds of ECG records. Finally, the results based on the class-oriented schema achieved an accuracy of 98.3% based on Resnet50 with the XGBoost classifier. The comparison with the related previous work presented the excellent performance of the proposed methodology as it can be applied as a clinical application.
Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks
Research Square (Research Square), 2021
Background: Electrocardiogram (ECG) is a method of recording the electrical activity of the heart and it provides a diagnostic means for heart-related diseases. Arrhythmia is any irregularity of the heartbeat that causes an abnormality in the heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG recordings is not practical for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to develop computer-aided-diagnosis (CAD) systems to automatically identify arrhythmias. Methods: This paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The proposed approach identifies arrhythmia classes using Convolutional Neural Network (CNN) trained by two-dimensional (2D) ECG beat images. Firstly, ECG signals, which consist of 5 different arrhythmias, are segmented into heartbeats which are transformed into 2D grayscale images. Afterward, the images are used as input for training a new CNN architecture to classify heartbeats. Results: The experimental results show that the classification performance of the proposed approach reaches an overall accuracy of 99.7%, sensitivity of 99.7%, and specificity of 99.22% in the classification of five different ECG arrhythmias. Further, the proposed CNN architecture is compared to other popular CNN architectures such as LeNet and ResNet-50 to evaluate the performance of the study. Conclusions: Test results demonstrate that the deep network trained by ECG images provides outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Moreover, the proposed method has lower computational costs compared to existing methods and is more suitable for mobile device-based diagnosis systems as it does not involve any complex preprocessing process. Hence, the proposed approach provides a simple and robust automatic cardiac arrhythmia detection scheme for the classification of ECG arrhythmias.
A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal
Sensors
Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model’s classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outpe...
A Model For Electrocardiogram (ECG) Classification Using Convolutional Neural Network (CNN
IJARCCE, 2021
Electrocardiogram (ECG) is an intermittent sign, which mirrors the movement of the heart. From ECG a great deal data is gotten for typical and obsessive physiology of heart. The ECG signal is non-fixed in nature and extremely hard to dissect. Clinical perception takes long time and the sign is non-fixed. This paper presents a convolutional neural network algorithm for electrocardiogram signal classification. This system uses a ECG dataset which was downloaded from kaggle.com. The dataset signals were preprocessed to make sure that each segment conforms to a heartbeat. This dataset was read into the jupyter notebook by using pandas.read_csv function. The dataset was made into two, which are the training data and the testing data. After successful reading of the data signal from directory and solving of the in balance problem by means of data augmentation, the proposed model was trained using a convolutional neural network(CNN) algorithm with a total hidden layers of six, hiden size of 128, batch_size of 96, and number of epoch to be 10. After successful training, we had an accuracy of 99% at an epoch level of 10. 1. INTRODUCTION Diseases influencing heart have gotten normal on daily basis. Diseases influencing heart is expanding as a result of present day feeble way of life increment in ailments like diabetes, hypertension and tobacco smoking. Heart can be influenced because of various conditions. Electrocardiogram (ECG) is one of the basic, effectively accessible, more affordable, effectively feasible, non-obtrusive examinations accessible at all spot incorporating provincial territories with insignificant framework. Specialists at the far off spots with fundamental clinical information may not be all around prepared to decipher an ECG. Appropriately diagnosing cardiovascular (heart related) condition at the most punctual is of most extreme significance. During these ailments, time matters the most. Consistently delay in treating them, trail to more harm in heart muscle bringing about antagonistic result. Consequently, exact distinguishing proof and early diagnosing these heart infections is vital. Anticipating patients into low and high danger is vital. Okay patients can be dealt with locally at a similar clinic with insignificant framework itself. High-hazard patients require early reference to cardiovascular reference clinics. ECG affirms or associates the finding with myocardial localized necrosis, arrhythmias and different conditions. When affirmed, they are treated with prescriptions or methodology (medical procedures) contingent upon the patient subtype and the offices accessible [1]. Electrocardiogram (ECG) is an intermittent sign, which mirrors the movement of the heart. From ECG a great deal data is gotten for typical and obsessive physiology of heart. The ECG signal is non-fixed in nature and extremely hard to dissect. Clinical perception takes long time and the sign is non-fixed. In this way, computer based method is utilized in ECG investigation. The rule of ECG signal is electrical movement. This is sent through the body and pick up on the skin. At last, the ECG machine records the action utilizing terminals and show graphically. The ECG signal comprises of dreary complex waveform with a recurrence estimation of 1 Hz. Each cardiovascular cycle comprises of three waves, for example, P wave QRS wave and T wave. These waves are delivered because of the capacity of atria and ventricular pieces of the heart. Cardiovascular illness is one of the significant reasons for death in the western reality where in excess of 16 million kick the bucket every year [2]. An Electro cardio realistic sign is recorded on a long timescale to recognize discontinuously happening aggravations in the heart musicality. To diminish the cardiovascular illnesses the way of life changes, for example, decreased cholesterol admission and customary exercise are obligatory. Early discovery is an essential advance in the cardiovascular sickness. To gauge the electrical sign from various pieces of heart two sorts of terminals are utilized. They are appendage anodes and chest terminals. The P wave is created by atrial depolarization, the length is under 120 ms, and this can be considered as low recurrence wave. ORS complex wave has span of 70-110 ms and T wave is delivered by the repolarization of ventricles having length more noteworthy than 300 ms [3]. Electrocardiogram (ECG) accounts are frequently debased by a lot of commotion and ancient rarities that can be inside the recurrence band of helpful heart information and can show with comparable morphologies to the ECG waveform itself [4]. Not exclusively does the presence of commotion and antiquity meddle with the right acknowledgment of QRS,
Comparative Evaluation for Two and Five Classes ECG Signal Classification: Applied Deep Learning
ECG can be using to reliably monitor the health of a cardiovascular system. The proper classification of heartbeats has received a lot of attention recently. While there are numerous similarities among ECG situations, instead of learning and to use transferable knowledge across tasks, most research has concentrated on classify a group of situations using a dataset labeled for that task. This research suggested a technique for heartbeat classification based using deep CNN models that can accurately categorize distinct arrhythmias for two and five classes ECG signals in line to AAMI EC57 standards. The authors also propose a strategy for transferring this job's knowledge to the myocardial infarction (MI) categorization problem. Physician Net's MIT-BIH and PTB Diagnostic databases were used to evaluate the suggested technique. The ECG data was gathered from various Physio Bank databases, which provide clinical research data freely available. Images of ECG signals with time-frequency encoding were fed into architecture such as CNN, LSTM, Alex Net, VGG-16, Resnet50, and Inception. The categorization of ECGs was completed, as well as the performance of CNN, LSTM, Alex Net, VGG-16, Resnet50, and Inception architectures were evaluated using a transfer learning technique and modifications in particular output layers for five designs.
Cardiac Arrhythmia Classification in Electrocardiogram Signals with Convolutional Neural Networks
Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM), 2023
Electrocardiography is a frequently used examination technique for heart disease diagnosis. Electrocardiography is essential in the clinical evaluation of patients who have heart disease. Through the electrocardiogram (ECG), medical doctors can identify whether the cardiac muscle dysfunctions presented by the patient have an inflammatory origin and early diagnosis of serious diseases that primarily affect the blood vessels and the brain. The basis of arrhythmia diagnosis is the identification of normal and abnormal heartbeats and their classification into different diagnoses based on ECG morphology. Heartbeats can be divided into five categories: non-ectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats. It is difficult to distinguish these heartbeats apart on the ECG as these signals are typically corrupted by outside noise. The objective of this study is to develop a classifier capable of classifying a patient's ECG signals for the detection of arrhythmia in clinical patients. We developed a convolutional neural network (CNN) to identify five categories of heartbeats in ECG signals. Our experiment was conducted with ECG signals obtained from a publicly available MIT-BIH database. The number of instances was even out to five classes of heartbeats. The proposed model achieved an accuracy of 99.33% and an F1-score of 99.44% in the classification of ventricular ectopic beats (VEB).
A Deep Learning Approach for Cardiac Arrhythmia Detection
International Journal for Research in Applied Science & Engineering Technology, 2020
Cardiac arrhythmia specifies uncommon electrical impulses of the heart that may be a major threat to humans. It should be reported for clinical evaluation and care. Electrocardiogram monitoring (ECG) measurements perform a significant part in the treatment of heart failure. Due to heartrate differences between individual patients and unknown disturbances in the ECG readings it is difficult for doctors to identify the type of arrhythmia. Classification plays an important role in health protection and computational biology. In this work, we aim to classify the heartbeats extracted from an ECG using deep learning, based only on the line shape (morphology) of the individual heartbeats. The goal would be to develop a method that automatically detects anomalies and help for prompt diagnosis of arrhythmia. A trained neural feed-forward network was chosen for this study. Experimental findings suggest that deep-learning models are more reliable than traditional cardiac diagnosis methods. The details used for the study of ECG signals were from the MIT-BIH database