ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification
Cardiovascular diseases, which are currently the major causes of death globally, can be largely ameliorated through early detection and categorization. Electrocardiogram (ECG) tests have emerged as widely employed, low-cost and non-invasive procedures for evaluating electrical activities of the hear...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10795116/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536165567528960 |
|---|---|
| author | Mudassar Khalid Charnchai Pluempitiwiriyawej Abdulkadhem A. Abdulkadhem Imran Afzal Tien Truong |
| author_facet | Mudassar Khalid Charnchai Pluempitiwiriyawej Abdulkadhem A. Abdulkadhem Imran Afzal Tien Truong |
| author_sort | Mudassar Khalid |
| collection | DOAJ |
| description | Cardiovascular diseases, which are currently the major causes of death globally, can be largely ameliorated through early detection and categorization. Electrocardiogram (ECG) tests have emerged as widely employed, low-cost and non-invasive procedures for evaluating electrical activities of the heart and diagnosing cardiovascular ailments. In this research, by using deep learning techniques to detect specific cardiac disorders like cardiac myocardial infarction(MI), arrhythmia, past history of myocardial infarction(PMI) and normal ECG patterns on a dataset containing patients with heart disease. We propose ECGConVT framework that combines Convolutional Neural Network (CNN) module for extracting local features, and Vision Transformer (ViT) module for capturing global features. The final classification is achieved by combining the two using Multilayer Perceptron (MLP) module. The experimental results indicate promise of ECGConVT in ECG image classification where it outperforms other approaches showing an average accuracy of 98.5%, F1-score: 98.7%, Recall: 98.8% and Precision: 98.5%. In order to meet the practical needs of clinical applications, we implemented a lightweight post-processing step to reduce the size of the model. |
| format | Article |
| id | doaj-art-38c86abc6dac4a26b4ef347a59fd08ff |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-38c86abc6dac4a26b4ef347a59fd08ff2025-01-15T00:02:07ZengIEEEIEEE Access2169-35362024-01-011219304319305610.1109/ACCESS.2024.351649510795116ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images ClassificationMudassar Khalid0https://orcid.org/0000-0001-9684-407XCharnchai Pluempitiwiriyawej1Abdulkadhem A. Abdulkadhem2https://orcid.org/0000-0002-4533-7083Imran Afzal3Tien Truong4https://orcid.org/0009-0004-2546-0043Department of Electrical Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Electrical Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Cyber Security, College of Sciences, Al-Mustaqbal University, Hillah, Babylon, IraqSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Economics and Cognitive Science, University of California at Berkeley, Berkeley, CA, USACardiovascular diseases, which are currently the major causes of death globally, can be largely ameliorated through early detection and categorization. Electrocardiogram (ECG) tests have emerged as widely employed, low-cost and non-invasive procedures for evaluating electrical activities of the heart and diagnosing cardiovascular ailments. In this research, by using deep learning techniques to detect specific cardiac disorders like cardiac myocardial infarction(MI), arrhythmia, past history of myocardial infarction(PMI) and normal ECG patterns on a dataset containing patients with heart disease. We propose ECGConVT framework that combines Convolutional Neural Network (CNN) module for extracting local features, and Vision Transformer (ViT) module for capturing global features. The final classification is achieved by combining the two using Multilayer Perceptron (MLP) module. The experimental results indicate promise of ECGConVT in ECG image classification where it outperforms other approaches showing an average accuracy of 98.5%, F1-score: 98.7%, Recall: 98.8% and Precision: 98.5%. In order to meet the practical needs of clinical applications, we implemented a lightweight post-processing step to reduce the size of the model.https://ieeexplore.ieee.org/document/10795116/Deep learningECG images classificationelectrocardiogrammachine learningvision transformer |
| spellingShingle | Mudassar Khalid Charnchai Pluempitiwiriyawej Abdulkadhem A. Abdulkadhem Imran Afzal Tien Truong ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification IEEE Access Deep learning ECG images classification electrocardiogram machine learning vision transformer |
| title | ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification |
| title_full | ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification |
| title_fullStr | ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification |
| title_full_unstemmed | ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification |
| title_short | ECGConVT: A Hybrid CNN and Vision Transformer Model for Enhanced 12-Lead ECG Images Classification |
| title_sort | ecgconvt a hybrid cnn and vision transformer model for enhanced 12 lead ecg images classification |
| topic | Deep learning ECG images classification electrocardiogram machine learning vision transformer |
| url | https://ieeexplore.ieee.org/document/10795116/ |
| work_keys_str_mv | AT mudassarkhalid ecgconvtahybridcnnandvisiontransformermodelforenhanced12leadecgimagesclassification AT charnchaipluempitiwiriyawej ecgconvtahybridcnnandvisiontransformermodelforenhanced12leadecgimagesclassification AT abdulkadhemaabdulkadhem ecgconvtahybridcnnandvisiontransformermodelforenhanced12leadecgimagesclassification AT imranafzal ecgconvtahybridcnnandvisiontransformermodelforenhanced12leadecgimagesclassification AT tientruong ecgconvtahybridcnnandvisiontransformermodelforenhanced12leadecgimagesclassification |