Cardiac Arrhythmia Recognition Using Transfer Learning with a Pre-trained DenseNet

Ullah, Hadaate; Bu, Yuxiang; Pan, Taisong; Gao, Min; Islam, Md. Sajjatul; Lin, Yuan; Lai, Dakun

doi:10.1109/prml52754.2021.9520710

Cited by 6 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They process the data repeatedly to acquire the optimal number of parameters during training; as a result, it may face the over-fitting problem with the small volume of datasets. This challenge could be addressed to employ the transfer learning technique [ 90 ] in the model that is trained on large volume of data previously. In addition, comprehending a relationship between the feature extraction and fundamental physiology is very important to recognize the specific disease.…”

Section: Resultsmentioning

confidence: 99%

An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal

Ullah

Heyat

AlSalman

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

Recently, cardiac arrhythmia recognition from electrocardiography (ECG) with deep learning approaches is becoming popular in clinical diagnosis systems due to its good prognosis findings, where expert data preprocessing and feature engineering are not usually required. But a lightweight and effective deep model is highly demanded to face the challenges of deploying the model in real-life applications and diagnosis accurately. In this work, two effective and lightweight deep learning models named Deep-SR and Deep-NSR are proposed to recognize ECG beats, which are based on two-dimensional convolution neural networks (2D CNNs) while using different structural regularizations. First, 97720 ECG beats extracted from all records of a benchmark MIT-BIH arrhythmia dataset have been transformed into 2D RGB (red, green, and blue) images that act as the inputs to the proposed 2D CNN models. Then, the optimization of the proposed models is performed through the proper initialization of model layers, on-the-fly augmentation, regularization techniques, Adam optimizer, and weighted random sampler. Finally, the performance of the proposed models is evaluated by a stratified 5-fold cross-validation strategy along with callback features. The obtained overall accuracy of recognizing normal beat and three arrhythmias (V-ventricular ectopic, S-supraventricular ectopic, and F-fusion) based on the Association for the Advancement of Medical Instrumentation (AAMI) is 99.93%, and 99.96% for the proposed Deep-SR model and Deep-NSR model, which demonstrate that the effectiveness of the proposed models has surpassed the state-of-the-art models and also expresses the higher model generalization. The received results with model size suggest that the proposed CNN models especially Deep-NSR could be more useful in wearable devices such as medical vests, bracelets for long-term monitoring of cardiac conditions, and in telemedicine to accurate diagnose the arrhythmia from ECG automatically. As a result, medical costs of patients and work pressure on physicians in medicals and clinics would be reduced effectively.

show abstract

Section: Resultsmentioning

confidence: 99%

An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal

Ullah

Heyat

AlSalman

et al. 2022

Journal of Healthcare Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Transfer learning is becoming popular nowadays due to handling the challenge of huge data demanding for deep model training (the most private and publicly available datasets are currently of small volume). In this approach, the model is not trained from scratch, so it helps to reduce the overfitting problem of a deep model [ 32 ] and enhance the computational efficiency. The mechanism could also be a prosperous solution for storage constraint devices in real-life applications.…”

Section: Resultsmentioning

confidence: 99%

“…is mechanism could easily solve the deep network overfitting problem. A few contributions to the literature address the transfer learning mechanism for detecting abnormalities in ECG signals [30][31][32][33]. In this type of approach, there is no requirement to develop a model from scratch.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Cardiac Arrhythmia Recognition Method with an Effective DenseNet Model on Imbalanced Datasets Using ECG Signal

Ullah

Heyat

Akhtar

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Electrocardiography (ECG) is a well-known noninvasive technique in medical science that provides information about the heart’s rhythm and current conditions. Automatic ECG arrhythmia diagnosis relieves doctors’ workload and improves diagnosis effectiveness and efficiency. This study proposes an automatic end-to-end 2D CNN (two-dimensional convolution neural networks) deep learning method with an effective DenseNet model for addressing arrhythmias recognition. To begin, the proposed model is trained and evaluated on the 97720 and 141404 beat images extracted from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia and St. Petersburg Institute of Cardiological Technics (INCART) datasets (both are imbalanced class datasets) using a stratified 5-fold evaluation strategy. The data is classified into four groups: N (normal), V (ventricular ectopic), S (supraventricular ectopic), and F (fusion), based on the Association for the Advancement of Medical Instrumentation® (AAMI). The experimental results show that the proposed model outperforms state-of-the-art models for recognizing arrhythmias, with the accuracy of 99.80% and 99.63%, precision of 98.34% and 98.94%, and F1-score of 98.91% and 98.91% on the MIT-BIH arrhythmia and INCART datasets, respectively. Using a transfer learning mechanism, the proposed model is also evaluated with only five individuals of supraventricular MIT-BIH arrhythmia and five individuals of European ST-T datasets (both of which are also class imbalanced) and achieved satisfactory results. So, the proposed model is more generalized and could be a prosperous solution for arrhythmias recognition from class imbalance datasets in real-life applications.

show abstract

“…In CNNs, one-dimensional CNN (1D CNN), two-dimensional CNN (2D CNN), and three-dimensional CNN (3D CNN) consider the time-series raw or preprocessed signals, equivalent images of raw or preprocessed signals, and videos of raw or preprocessed signals, respectively, as its input. The 2D CNN provides better performance compared to 1D CNN [ 122 , 123 ]. Dong et al [ 48 ] designed a soft multi-functional electronic skin (SMFES) to collect several vital signs (sweat and temperature) and EOGs from the human body for the detection of eye movement for wearable applications.…”

Section: Body-to-electrode Signal Transduction and Measurementsmentioning

confidence: 99%

“…Several studies [ 18 , 21 , 22 , 115 , 116 ], which used capacitive sensors for long-term monitoring, have achieved good signal-to-noise ratios (SNRs). Capacitive sensors also have great potential for disease identification using machine learning algorithms adopting strategies such as feature engineering [ 117 , 118 ] and deep learning [ 119 , 120 , 121 , 122 , 123 ].…”

Section: Introductionmentioning

confidence: 99%

Recent Advances in Stretchable and Wearable Capacitive Electrophysiological Sensors for Long-Term Health Monitoring

et al. 2022

Self Cite

View full text Add to dashboard Cite

Over the past several years, wearable electrophysiological sensors with stretchability have received significant research attention because of their capability to continuously monitor electrophysiological signals from the human body with minimal body motion artifacts, long-term tracking, and comfort for real-time health monitoring. Among the four different sensors, i.e., piezoresistive, piezoelectric, iontronic, and capacitive, capacitive sensors are the most advantageous owing to their reusability, high durability, device sterilization ability, and minimum leakage currents between the electrode and the body to reduce the health risk arising from any short circuit. This review focuses on the development of wearable, flexible capacitive sensors for monitoring electrophysiological conditions, including the electrode materials and configuration, the sensing mechanisms, and the fabrication strategies. In addition, several design strategies of flexible/stretchable electrodes, body-to-electrode signal transduction, and measurements have been critically evaluated. We have also highlighted the gaps and opportunities needed for enhancing the suitability and practical applicability of wearable capacitive sensors. Finally, the potential applications, research challenges, and future research directions on stretchable and wearable capacitive sensors are outlined in this review.

show abstract

Cardiac Arrhythmia Recognition Using Transfer Learning with a Pre-trained DenseNet

Cited by 6 publications

References 10 publications

An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal

An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal

An End-to-End Cardiac Arrhythmia Recognition Method with an Effective DenseNet Model on Imbalanced Datasets Using ECG Signal

Recent Advances in Stretchable and Wearable Capacitive Electrophysiological Sensors for Long-Term Health Monitoring

Contact Info

Product

Resources

About