1
|
Zhu F, Ding J, Li X, Lu Y, Liu X, Jiang F, Zhao Q, Su H, Shuai J. MEAs-Filter: a novel filter framework utilizing evolutionary algorithms for cardiovascular diseases diagnosis. Health Inf Sci Syst 2024; 12:8. [PMID: 38274493 PMCID: PMC10805910 DOI: 10.1007/s13755-023-00268-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 12/27/2023] [Indexed: 01/27/2024] Open
Abstract
Cardiovascular disease management often involves adjusting medication dosage based on changes in electrocardiogram (ECG) signals' waveform and rhythm. However, the diagnostic utility of ECG signals is often hindered by various types of noise interference. In this work, we propose a novel filter based on a multi-engine evolution framework named MEAs-Filter to address this issue. Our approach eliminates the need for predefined dimensions and allows adaptation to diverse ECG morphologies. By leveraging state-of-the-art optimization algorithms as evolution engine and incorporating prior information inputs from classical filters, MEAs-Filter achieves superior performance while minimizing order. We evaluate the effectiveness of MEAs-Filter on a real ECG database and compare it against commonly used filters such as the Butterworth, Chebyshev filters, and evolution algorithm-based (EA-based) filters. The experimental results indicate that MEAs-Filter outperforms other filters by achieving a reduction of approximately 30% to 60% in terms of the loss function compared to the other algorithms. In denoising experiments conducted on ECG waveforms across various scenarios, MEAs-Filter demonstrates an improvement of approximately 20% in signal-to-noise (SNR) ratio and a 9% improvement in correlation. Moreover, it does not exhibit higher losses of the R-wave compared to other filters. These findings highlight the potential of MEAs-Filter as a valuable tool for high-fidelity extraction of ECG signals, enabling accurate diagnosis in the field of cardiovascular diseases.
Collapse
Affiliation(s)
- Fangfang Zhu
- Department of Physics, and Fujian Provincial Key Laboratory for Soft Functional Materials Research, Xiamen University, Xiamen, 361005 China
- National Institute for Data Science in Health and Medicine, and State Key Laboratory of Cellular Stress Biology, Innovation Center for Cell Signaling Network, Xiamen University, Xiamen, 361005 China
| | - Ji Ding
- Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, 314006 China
| | - Xiang Li
- Department of Physics, and Fujian Provincial Key Laboratory for Soft Functional Materials Research, Xiamen University, Xiamen, 361005 China
| | - Yuer Lu
- Wenzhou Institute and Wenzhou Key Laboratory of Biophysics, University of Chinese Academy of Sciences, Wenzhou, 325001 China
| | - Xiao Liu
- School of Information Technology, Faculty of Science, Engineering and Built Environment, Deakin University, Geelong, VIC Australia
| | - Frank Jiang
- School of Information Technology, Faculty of Science, Engineering and Built Environment, Deakin University, Geelong, VIC Australia
| | - Qi Zhao
- School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, 114051 China
| | - Honghong Su
- Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, 314006 China
| | - Jianwei Shuai
- Wenzhou Institute and Wenzhou Key Laboratory of Biophysics, University of Chinese Academy of Sciences, Wenzhou, 325001 China
| |
Collapse
|
2
|
Yang Y, Chen L, Wu S. Enhancing Fetal Electrocardiogram Signal Extraction Accuracy through a CycleGAN Utilizing Combined CNN-BiLSTM Architecture. SENSORS (BASEL, SWITZERLAND) 2024; 24:2948. [PMID: 38733053 PMCID: PMC11086239 DOI: 10.3390/s24092948] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 04/27/2024] [Accepted: 05/01/2024] [Indexed: 05/13/2024]
Abstract
The fetal electrocardiogram (FECG) records changes in the graph of fetal cardiac action potential during conduction, reflecting the developmental status of the fetus in utero and its physiological cardiac activity. Morphological alterations in the FECG can indicate intrauterine hypoxia, fetal distress, and neonatal asphyxia early on, enhancing maternal and fetal safety through prompt clinical intervention, thereby reducing neonatal morbidity and mortality. To reconstruct FECG signals with clear morphological information, this paper proposes a novel deep learning model, CBLS-CycleGAN. The model's generator combines spatial features extracted by the CNN with temporal features extracted by the BiLSTM network, thus ensuring that the reconstructed signals possess combined features with spatial and temporal dependencies. The model's discriminator utilizes PatchGAN, employing small segments of the signal as discriminative inputs to concentrate the training process on capturing signal details. Evaluating the model using two real FECG signal databases, namely "Abdominal and Direct Fetal ECG Database" and "Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeat Annotations", resulted in a mean MSE and MAE of 0.019 and 0.006, respectively. It detects the FQRS compound wave with a sensitivity, positive predictive value, and F1 of 99.51%, 99.57%, and 99.54%, respectively. This paper's model effectively preserves the morphological information of FECG signals, capturing not only the FQRS compound wave but also the fetal P-wave, T-wave, P-R interval, and ST segment information, providing clinicians with crucial diagnostic insights and a scientific foundation for developing rational treatment protocols.
Collapse
Affiliation(s)
| | | | - Shuicai Wu
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China; (Y.Y.); (L.C.)
| |
Collapse
|
3
|
Mvuh FL, Ebode Ko'a COV, Bodo B. Multichannel high noise level ECG denoising based on adversarial deep learning. Sci Rep 2024; 14:801. [PMID: 38191583 PMCID: PMC10774433 DOI: 10.1038/s41598-023-50334-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2023] [Accepted: 12/19/2023] [Indexed: 01/10/2024] Open
Abstract
This paper proposes a denoising method based on an adversarial deep learning approach for the post-processing of multi-channel fetal electrocardiogram (ECG) signals. As it's well known, noise leads to misinterpretations of fetal ECG signals and thus limits the use of fetal electrocardiography for healthcare applications. Therefore, denoising algorithms are essential for the exploitation of non-invasive fetal ECG. The proposed method is based on the combination of three end-to-end trained sub-networks to convert noisy fetal ECG signals into clean signals. The first two sub-networks are linked by skip connections and form a deep convolutional network that downsamples the noisy signals into a latent representation and subsequently upsamples this latent representation to recover clean signals. The third sub-network aims to boost the decoder sub-network to generate realistic clean signals. Experiments carried out on synthetic and real data showed that the proposed method improved by the signal-to-noise (SNR) of fetal ECG signals with input SNR ranging from [Formula: see text] to 0 dB by an average of 20 dB, and improve fetal signal quality by significantly increasing the number of true detected QRS complexes and halving QRS complex detection errors.
Collapse
Affiliation(s)
- Franck Lino Mvuh
- Departement of Physics, University of Yaoundé 1, PO.BOX 812, Yaoundé, Cameroon
| | | | - Bertrand Bodo
- Departement of Physics, University of Yaoundé 1, PO.BOX 812, Yaoundé, Cameroon.
| |
Collapse
|
4
|
Jaros R, Tomicova E, Martinek R. Template subtraction based methods for non-invasive fetal electrocardiography extraction. Sci Rep 2024; 14:630. [PMID: 38182757 PMCID: PMC10770155 DOI: 10.1038/s41598-024-51213-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Accepted: 01/02/2024] [Indexed: 01/07/2024] Open
Abstract
Assessment of fetal heart rate (fHR) through non-invasive fetal electrocardiogram (fECG) is challenging task. This study compares the performance of five template subtraction (TS) methods on Labor (12 5-min recordings) and Pregnancy datasets (10 20-min recordings). The methods include TS without adaptation, TS using singular value decomposition (TS[Formula: see text]), TS using linear prediction (TS[Formula: see text]), TS using scaling factor (TS[Formula: see text]), and sequential analysis (SA). The influence of the chosen maternal wavelet for the continuous wavelet transform (CWT) detector is also compared. The F1 score was used to measure performance. Each recording in both datasets consisted of four signals, resulting in a total comparison of 88 signals for the TS-based methods. The study reported the following results: F1 = 95.71% with TS, F1 = 95.93% with TS[Formula: see text], F1 = 95.30% with TS[Formula: see text], F1 = 95.82% with TS[Formula: see text], and F1 = 95.99% with SA. The study identified gaus3 as the suitable maternal wavelet for fetal R-peak detection using the CWT detector. Furthermore, the study classified signals from the tested datasets into categories of high, medium, and low quality, providing valuable insights for subsequent fECG signal extraction. This research contributes to advancing the understanding of non-invasive fECG signal processing and lays the groundwork for improving fetal monitoring in clinical settings.
Collapse
Affiliation(s)
- Rene Jaros
- Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 17. listopadu 2172/15, 708 00, Ostrava, Czechia.
| | - Eva Tomicova
- Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 17. listopadu 2172/15, 708 00, Ostrava, Czechia
| | - Radek Martinek
- Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 17. listopadu 2172/15, 708 00, Ostrava, Czechia
| |
Collapse
|
5
|
Tanasković I, Miljković N. A new algorithm for fetal heart rate detection: Fractional order calculus approach. Med Eng Phys 2023; 118:104007. [PMID: 37536830 DOI: 10.1016/j.medengphy.2023.104007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2023] [Revised: 05/23/2023] [Accepted: 06/15/2023] [Indexed: 08/05/2023]
Abstract
OBJECTIVES A new modified Pan-Tompkins' (mPT) method for fetal heart rate detection is presented. The mPT method is based on the hypothesis that optimal fractional order derivative and optimal window width of the moving average filter would enable efficient estimation of fetal heart rate from surface abdominal electrophysiological recordings with relatively low signal-to-noise ratios. METHODS The algorithm is tested on signals recorded from the abdomen of pregnant women available from the PhysioNet Computing in Cardiology Challenge database. Fetal heart rate detection is performed on 10-s long segments selected by the estimation of signal-to-noise ratios (the extravagance of the fetal QRS peak to its surroundings and to the whole signal; and the mean ratio of fetal and maternal QRS peaks) and on the manually selected segments. RESULTS The best results are obtained via criteria based on the extravagance of the fetal QRS peak to its surroundings that reached average sensitivity of 97%, positive predictive value of 97%, error rate of ∼3.5%, and F1 score of 97%. The obtained averaged optimal parameters for mPT are 0.51 for fractional order and 24.5 ms for the window width of the moving average filter. CONCLUSION Proposed mPT algorithm showed satisfactory performance for fetal heart rate detection. Further adaptations of the presented mPT method could be used for peak detection in noisy environments in biomedical signal analysis in general.
Collapse
Affiliation(s)
- Ilija Tanasković
- University of Belgrade - School of Electrical Engineering, Bulevar kralja Aleksandra 73, 11000 Belgrade, Serbia; Institute for Artificial Intelligence R&D, Fruskogorska 1, 21000 Novi Sad, Serbia
| | - Nadica Miljković
- University of Belgrade - School of Electrical Engineering, Bulevar kralja Aleksandra 73, 11000 Belgrade, Serbia; Faculty of Electrical Engineering, University of Ljubljana. Tržaška c. 25, 1000 Ljubljana, Slovenia.
| |
Collapse
|
6
|
Wang X, Han Y, Deng Y. CSGSA-Net: Canonical-structured graph sparse attention network for fetal ECG estimation. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104556] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
|
7
|
Wang X, Han Y, Deng Y. ASW-Net: Adaptive Spectral Wavelet Network for Accurate Fetal ECG Extraction. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2022; 16:1387-1396. [PMID: 36301783 DOI: 10.1109/tbcas.2022.3217464] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
Noninvasive fetal ECG (FECG) is of great significance for monitoring fetal health. However, it is challenging to extract FECG signals from the abdominal ECG signal (AECG) due to the complexity of the task: 1) FECG signals are routinely mixed with noise; 2) FECG signals are aliased with maternal ECG signals in the time and frequency domain. To solve such problems, an adaptive spectral wavelet network (ASW-Net) is proposed for FECG extraction, where the adaptive spectral wavelet module, which can improve the computational efficiency by replacing convolution operation with element-wise Hadamard product in the frequency domain, is first developed to extract FECG components with different frequencies; then, the residual attention module is devised to distinguish FECG signals from noise by capturing waveform details; finally, the inverse spectral wavelet module is designed to reconstruct FECG signals from multi-resolution FECG components. Experiments conducted on the benchmarks demonstrate that the proposed ASW-Net outperforms the state-of-the-art methods.
Collapse
|
8
|
D ED, M S. Extraction of Fetal ECG From Abdominal and Thorax ECG Using a Non-Causal Adaptive Filter Architecture. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2022; 16:981-990. [PMID: 36074866 DOI: 10.1109/tbcas.2022.3204993] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Extracting the Electrocardiogram (ECG) of a fetus from the ECG signal of the maternal abdomen is a challenging task due to different artifacts. The paper proposes a N-tap non-causal adaptive filter (NC-AF) that update the weight by considering the N number of past weights and N-1 number of the reference signal and error signal samples after the processing sample number n. Using the maternal abdominal signal as the primary signal and thorax signal as the reference input, the output e(n) is obtained from the mean of N number of errors. The filtering performance of NC-AF was evaluated using the Synthetic dataset and Daisy dataset with the metrics such as correlation coefficient ( γ), peak root mean square difference (PRD), the output signal to noise ratio (SNR), root mean square error (RMSE), and fetal R-peak detection accuracy (FRPDA). The NC-AF provides a maximum correlation coefficient, PRD, SNR, RMSE and FRPDA of 0.9851, 83.04%, 8.52 dB, 0.208 and 97.09% respectively with filter length N=38. The paper also proposes the architecture of NC-AF that can be implemented in hardware like FPGA. Further, the NC-AF was implemented on Virtex-7 FPGA and its performance is evaluated in terms of resource utilization, throughput, and power consumption. For filter length N=38 and wordlength L=24, the maximum performance of the filter can be attained with a power consumption of [Formula: see text] and a maximum clock frequency of 139.47 MHz.
Collapse
|
9
|
Fetal Electrocardiogram Signal Extraction Based on Fast Independent Component Analysis and Singular Value Decomposition. SENSORS 2022; 22:s22103705. [PMID: 35632114 PMCID: PMC9146186 DOI: 10.3390/s22103705] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Revised: 05/06/2022] [Accepted: 05/09/2022] [Indexed: 02/04/2023]
Abstract
Fetal electrocardiograms (FECGs) provide important clinical information for early diagnosis and intervention. However, FECG signals are extremely weak and are greatly influenced by noises. FECG signal extraction and detection are still challenging. In this work, we combined the fast independent component analysis (FastICA) algorithm with singular value decomposition (SVD) to extract FECG signals. The improved wavelet mode maximum method was applied to detect QRS waves and ST segments of FECG signals. We used the abdominal and direct fetal ECG database (ADFECGDB) and the Cardiology Challenge Database (PhysioNet2013) to verify the proposed algorithm. The signal-to-noise ratio of the best channel signal reached 45.028 dB and the issue of missing waveforms was addressed. The sensitivity, positive predictive value and F1 score of fetal QRS wave detection were 96.90%, 98.23%, and 95.24%, respectively. The proposed algorithm may be used as a new method for FECG signal extraction and detection.
Collapse
|