Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images
Abstract Background As the incidence and prevalence of Atrial Fibrillation (AF) proliferate worldwide, the condition has become the epicenter of a plethora of ECG diagnostic research. In recent diagnostic methodologies, Morse Continuous Wavelet Transform (MsCWT) is a feature extraction technique uti...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-025-02872-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585617568956416 |
|---|---|
| author | Ling-Chun Sun Chia-Chiang Lee Hung-Yen Ke Chih-Yuan Wei Ke-Feng Lin Shih-Sung Lin Hsin Hsiu Ping-Nan Chen |
| author_facet | Ling-Chun Sun Chia-Chiang Lee Hung-Yen Ke Chih-Yuan Wei Ke-Feng Lin Shih-Sung Lin Hsin Hsiu Ping-Nan Chen |
| author_sort | Ling-Chun Sun |
| collection | DOAJ |
| description | Abstract Background As the incidence and prevalence of Atrial Fibrillation (AF) proliferate worldwide, the condition has become the epicenter of a plethora of ECG diagnostic research. In recent diagnostic methodologies, Morse Continuous Wavelet Transform (MsCWT) is a feature extraction technique utilized to draw out distinctive attributes of ECG signals. In our study, we explore the employment of MsCWT in the classification of AF with ECG signals in a continuum. Results We present a MsCWT image-based deep learning machine for AF differentiation. For the training, validation, and test sets, we achieved average accuracies of 97.94%, 97.84%, and 91.32%; and overall F1 scores of 97.13%, 96.86%, and 89.41% respectively. Moreover, AUC ROC curves of over 0.99 were obtained for all classes in the training and validation sets; and were over 0.9679 for the test set. Conclusions Training deep learning machines for the classification of AF with MsCWT-based images demonstrated to yield favorable outcomes and achieved superior performance amongst studies utilizing the same dataset. Though minimal, the conversion of signals into wavelet form with MsCWT may drastically improve outcomes not only in future ECG signal studies; but all signal-based diagnostics. |
| format | Article |
| id | doaj-art-1c39abc36cb04c9ea5d6ed41f93c4e94 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-1c39abc36cb04c9ea5d6ed41f93c4e942025-01-26T12:36:48ZengBMCBMC Medical Informatics and Decision Making1472-69472025-01-0122S511210.1186/s12911-025-02872-5Deep learning for the classification of atrial fibrillation using wavelet transform-based visual imagesLing-Chun Sun0Chia-Chiang Lee1Hung-Yen Ke2Chih-Yuan Wei3Ke-Feng Lin4Shih-Sung Lin5Hsin Hsiu6Ping-Nan Chen7School of Medicine, National Defense Medical CenterGraduate Institute of Applied Science and Technology, National Taiwan University of Science and TechnologyDivision of Cardiovascular Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical CenterGraduate Institute of Life Sciences, National Defense Medical CenterSchool of Public Health, National Defense Medical CenterDepartment of Computer Science and Information Engineering, Chinese Culture UniversityGraduate Institute of Biomedical Engineering, National Taiwan University of Science and TechnologyDepartment of Biomedical Engineering, National Defense Medical Center, TaiwanAbstract Background As the incidence and prevalence of Atrial Fibrillation (AF) proliferate worldwide, the condition has become the epicenter of a plethora of ECG diagnostic research. In recent diagnostic methodologies, Morse Continuous Wavelet Transform (MsCWT) is a feature extraction technique utilized to draw out distinctive attributes of ECG signals. In our study, we explore the employment of MsCWT in the classification of AF with ECG signals in a continuum. Results We present a MsCWT image-based deep learning machine for AF differentiation. For the training, validation, and test sets, we achieved average accuracies of 97.94%, 97.84%, and 91.32%; and overall F1 scores of 97.13%, 96.86%, and 89.41% respectively. Moreover, AUC ROC curves of over 0.99 were obtained for all classes in the training and validation sets; and were over 0.9679 for the test set. Conclusions Training deep learning machines for the classification of AF with MsCWT-based images demonstrated to yield favorable outcomes and achieved superior performance amongst studies utilizing the same dataset. Though minimal, the conversion of signals into wavelet form with MsCWT may drastically improve outcomes not only in future ECG signal studies; but all signal-based diagnostics.https://doi.org/10.1186/s12911-025-02872-5Atrial fibrillationMsCWTConvolutional Neural NetworkResNet101 |
| spellingShingle | Ling-Chun Sun Chia-Chiang Lee Hung-Yen Ke Chih-Yuan Wei Ke-Feng Lin Shih-Sung Lin Hsin Hsiu Ping-Nan Chen Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images BMC Medical Informatics and Decision Making Atrial fibrillation MsCWT Convolutional Neural Network ResNet101 |
| title | Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images |
| title_full | Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images |
| title_fullStr | Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images |
| title_full_unstemmed | Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images |
| title_short | Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images |
| title_sort | deep learning for the classification of atrial fibrillation using wavelet transform based visual images |
| topic | Atrial fibrillation MsCWT Convolutional Neural Network ResNet101 |
| url | https://doi.org/10.1186/s12911-025-02872-5 |
| work_keys_str_mv | AT lingchunsun deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT chiachianglee deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT hungyenke deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT chihyuanwei deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT kefenglin deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT shihsunglin deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT hsinhsiu deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages AT pingnanchen deeplearningfortheclassificationofatrialfibrillationusingwavelettransformbasedvisualimages |