ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images
Heart disease is a major health issue, and accurate diagnosis of irregular heartbeats and heart failure is crucial. Current diagnostic processes can be time-consuming, requiring significant effort from clinicians. An effective classifier, ADCGNet: Attention-based Dual Channel Gabor Network is propos...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823003178 |
| _version_ | 1797629709592297472 |
|---|---|
| author | Joseph Roger Arhin Xiaoling Zhang Kenneth Coker Isaac Osei Agyemang Wisdom Kwame Attipoe Francis Sam Isaac Adjei-Mensah Emmanuel Agyei |
| author_facet | Joseph Roger Arhin Xiaoling Zhang Kenneth Coker Isaac Osei Agyemang Wisdom Kwame Attipoe Francis Sam Isaac Adjei-Mensah Emmanuel Agyei |
| author_sort | Joseph Roger Arhin |
| collection | DOAJ |
| description | Heart disease is a major health issue, and accurate diagnosis of irregular heartbeats and heart failure is crucial. Current diagnostic processes can be time-consuming, requiring significant effort from clinicians. An effective classifier, ADCGNet: Attention-based Dual Channel Gabor Network is proposed to address this challenge by accurately classifying anomalies. ADCGNet involves pre-processing every ECG beat into two-dimensional images using Analytical Morlet transform and then applying thirty-two Gabor filters and Sobel edge detection to enhance features. ADCGNet comprises three blocks, with the first block using dual channels to extract essential features in the images efficiently. The second block includes a multi-head attention mechanism to focus on relevant features, and the third block uses a SoftMax activation function to perform classification tasks. Extensive experiments with public datasets from PhysioNet, and comparison with several state-of-the-art classifiers indicate ADCGNet is superior. Specifically, ADCGNet achieved an accuracy of 99.17%, 98.98% in precision, a recall of 98.87%, an F1-score of 98.82% and AUC, 98.75% with optimal hyperparameters. Further, a GRAD-CAM visualization of activated areas on the test samples gives graphical insight into the performance of ADCGNet. The proposed ADCGNet classifier has promising potential for enhancing the diagnosis of heart disease, and we believe it will be of much interest to the medical community. |
| first_indexed | 2024-03-11T10:57:54Z |
| format | Article |
| id | doaj.art-173bcc754b43410496eeb2da8d35369a |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-11T10:57:54Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-173bcc754b43410496eeb2da8d35369a2023-11-13T04:09:01ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-10-01359101763ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram imagesJoseph Roger Arhin0Xiaoling Zhang1Kenneth Coker2Isaac Osei Agyemang3Wisdom Kwame Attipoe4Francis Sam5Isaac Adjei-Mensah6Emmanuel Agyei7School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China; Corresponding author.School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China; Department of Electrical and Electronic Engineering, Ho Technical University, Ho 00233, GhanaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaDepartment of Mathematics, Clarkson University, NY, USASchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaHeart disease is a major health issue, and accurate diagnosis of irregular heartbeats and heart failure is crucial. Current diagnostic processes can be time-consuming, requiring significant effort from clinicians. An effective classifier, ADCGNet: Attention-based Dual Channel Gabor Network is proposed to address this challenge by accurately classifying anomalies. ADCGNet involves pre-processing every ECG beat into two-dimensional images using Analytical Morlet transform and then applying thirty-two Gabor filters and Sobel edge detection to enhance features. ADCGNet comprises three blocks, with the first block using dual channels to extract essential features in the images efficiently. The second block includes a multi-head attention mechanism to focus on relevant features, and the third block uses a SoftMax activation function to perform classification tasks. Extensive experiments with public datasets from PhysioNet, and comparison with several state-of-the-art classifiers indicate ADCGNet is superior. Specifically, ADCGNet achieved an accuracy of 99.17%, 98.98% in precision, a recall of 98.87%, an F1-score of 98.82% and AUC, 98.75% with optimal hyperparameters. Further, a GRAD-CAM visualization of activated areas on the test samples gives graphical insight into the performance of ADCGNet. The proposed ADCGNet classifier has promising potential for enhancing the diagnosis of heart disease, and we believe it will be of much interest to the medical community.http://www.sciencedirect.com/science/article/pii/S1319157823003178ArrhythmiaGabor filtersCongestive heart failureAnalytic Morlet transformNormal sinus rhythmElectrocardiogram |
| spellingShingle | Joseph Roger Arhin Xiaoling Zhang Kenneth Coker Isaac Osei Agyemang Wisdom Kwame Attipoe Francis Sam Isaac Adjei-Mensah Emmanuel Agyei ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images Journal of King Saud University: Computer and Information Sciences Arrhythmia Gabor filters Congestive heart failure Analytic Morlet transform Normal sinus rhythm Electrocardiogram |
| title | ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images |
| title_full | ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images |
| title_fullStr | ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images |
| title_full_unstemmed | ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images |
| title_short | ADCGNet: Attention-based dual channel Gabor network towards efficient detection and classification of electrocardiogram images |
| title_sort | adcgnet attention based dual channel gabor network towards efficient detection and classification of electrocardiogram images |
| topic | Arrhythmia Gabor filters Congestive heart failure Analytic Morlet transform Normal sinus rhythm Electrocardiogram |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823003178 |
| work_keys_str_mv | AT josephrogerarhin adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT xiaolingzhang adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT kennethcoker adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT isaacoseiagyemang adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT wisdomkwameattipoe adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT francissam adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT isaacadjeimensah adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages AT emmanuelagyei adcgnetattentionbaseddualchannelgabornetworktowardsefficientdetectionandclassificationofelectrocardiogramimages |