Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning
Purpose: The mortality rate of fetuses due to heart defects is a major concern for clinicians. The fetus's heart is monitored non-invasively using the abdominal Electrocardiogram (ECG) of the mother. Most of the methods in literature diagnose fetal arrhythmia based on fetal heart rate. However...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tehran University of Medical Sciences
2023-09-01
|
| Series: | Frontiers in Biomedical Technologies |
| Subjects: | |
| Online Access: | https://fbt.tums.ac.ir/index.php/fbt/article/view/514 |
| _version_ | 1797658928911220736 |
|---|---|
| author | Ashutosh Singh Rajeev Kumar Rai Ranjeet Srivastva Gyanendra Kumar |
| author_facet | Ashutosh Singh Rajeev Kumar Rai Ranjeet Srivastva Gyanendra Kumar |
| author_sort | Ashutosh Singh |
| collection | DOAJ |
| description |
Purpose: The mortality rate of fetuses due to heart defects is a major concern for clinicians. The fetus's heart is monitored non-invasively using the abdominal Electrocardiogram (ECG) of the mother. Most of the methods in literature diagnose fetal arrhythmia based on fetal heart rate. However, there are various challenges in fetal heart rate monitoring and arrhythmia detection. Therefore, very few methods are explored for fetal arrhythmia classification and have not achieved promising results.
Materials and Methods: In this article, a fetal arrhythmia classification method is investigated. The method has exploited the transfer learning principle where DenseNet architecture is utilized to learn fetal ECG patterns. Fetal ECG (fECG) signal extracted from the mothers abdominal has been processed for denoising and heartbeats are segmented using signal processing techniques. The extracted heartbeats have transformed into 2D fECG images to re-train the pre-trained DenseNet architecture.
Results: The proposed method has been evaluated on the publicly available Non-Invasive Fetal Arrhythmia Database (NIFADB) of Physionet and achieved 98.56% classification accuracy, thus outperforming other existing methods.
Conclusion: The arrhythmia in a fetus can be detected using a non-invasive fetal ECG. Due to the faster convergence of the learning algorithm, the proposed method offers better fetal diagnosis in real-time.
|
| first_indexed | 2024-03-11T18:07:36Z |
| format | Article |
| id | doaj.art-bc2e321faae34681bb63a2a00c358022 |
| institution | Directory Open Access Journal |
| issn | 2345-5837 |
| language | English |
| last_indexed | 2024-03-11T18:07:36Z |
| publishDate | 2023-09-01 |
| publisher | Tehran University of Medical Sciences |
| record_format | Article |
| series | Frontiers in Biomedical Technologies |
| spelling | doaj.art-bc2e321faae34681bb63a2a00c3580222023-10-17T05:06:43ZengTehran University of Medical SciencesFrontiers in Biomedical Technologies2345-58372023-09-0110410.18502/fbt.v10i4.13723Fetal ECG Arrhythmia Detection Based on DensNet Transfer LearningAshutosh Singh0Rajeev Kumar Rai1Ranjeet Srivastva2Gyanendra Kumar3Department of Computer Science, Keshav Mahavidyalay, University of Delhi, Delhi, IndiaDepartment of Computer Science, Aryabhatta College, University of Delhi, Delhi, IndiaDr. A.P.J. Abdul Kalam Technical University, Uttar Pradesh LucknowDepartment of Computer Science & Engineering, Babu Banarasi Das Institute of Technology and Management, Lucknow, India Purpose: The mortality rate of fetuses due to heart defects is a major concern for clinicians. The fetus's heart is monitored non-invasively using the abdominal Electrocardiogram (ECG) of the mother. Most of the methods in literature diagnose fetal arrhythmia based on fetal heart rate. However, there are various challenges in fetal heart rate monitoring and arrhythmia detection. Therefore, very few methods are explored for fetal arrhythmia classification and have not achieved promising results. Materials and Methods: In this article, a fetal arrhythmia classification method is investigated. The method has exploited the transfer learning principle where DenseNet architecture is utilized to learn fetal ECG patterns. Fetal ECG (fECG) signal extracted from the mothers abdominal has been processed for denoising and heartbeats are segmented using signal processing techniques. The extracted heartbeats have transformed into 2D fECG images to re-train the pre-trained DenseNet architecture. Results: The proposed method has been evaluated on the publicly available Non-Invasive Fetal Arrhythmia Database (NIFADB) of Physionet and achieved 98.56% classification accuracy, thus outperforming other existing methods. Conclusion: The arrhythmia in a fetus can be detected using a non-invasive fetal ECG. Due to the faster convergence of the learning algorithm, the proposed method offers better fetal diagnosis in real-time. https://fbt.tums.ac.ir/index.php/fbt/article/view/514Fetal ECGArrhythmiaTransfer LearningDenseNet |
| spellingShingle | Ashutosh Singh Rajeev Kumar Rai Ranjeet Srivastva Gyanendra Kumar Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning Frontiers in Biomedical Technologies Fetal ECG Arrhythmia Transfer Learning DenseNet |
| title | Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning |
| title_full | Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning |
| title_fullStr | Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning |
| title_full_unstemmed | Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning |
| title_short | Fetal ECG Arrhythmia Detection Based on DensNet Transfer Learning |
| title_sort | fetal ecg arrhythmia detection based on densnet transfer learning |
| topic | Fetal ECG Arrhythmia Transfer Learning DenseNet |
| url | https://fbt.tums.ac.ir/index.php/fbt/article/view/514 |
| work_keys_str_mv | AT ashutoshsingh fetalecgarrhythmiadetectionbasedondensnettransferlearning AT rajeevkumarrai fetalecgarrhythmiadetectionbasedondensnettransferlearning AT ranjeetsrivastva fetalecgarrhythmiadetectionbasedondensnettransferlearning AT gyanendrakumar fetalecgarrhythmiadetectionbasedondensnettransferlearning |