Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Jaba Deva Krupa Abel et al.
Summary: Despite the rapid growth in the field of adult ECG signal processing and monitoring systems, the analysis of fetal ECG signals lags behind and requires attention. Non-invasive fetal Electrocardiography is the safest method for monitoring fetal health by processing abdominal ECG (AECG) signals acquired by placing electrodes on the mother's abdomen. The primary challenge is the low signal-to-noise ratio of the recorded signal due to the dominant maternal ECG and other interferences present in the AECG signal. This paper provides an extensive review of existing techniques for extracting fetal ECG signals from AECG signals, including modeling methods, challenges with electrode placements, morphological analysis, and evaluation metrics.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Review
Obstetrics & Gynecology
Mark I. Evans et al.
Summary: Electronic fetal monitoring is the centerpiece of labor management, but its routine use has led to increased cesarean delivery rates. Our modified approach, called the Fetal Reserve Index, accurately identifies babies born with cerebral palsy and could reduce emergency cesarean deliveries. This index provides a good surrogate for fetal pH and base excess values.
AMERICAN JOURNAL OF OBSTETRICS AND GYNECOLOGY
(2023)
Article
Computer Science, Theory & Methods
Lakhan Dev Sharma et al.
Summary: Arrhythmia is a cardiac conduction disorder that leads to irregular heartbeats. The visual analysis of electrocardiograph (ECG) signals is challenging and time-consuming, but an automated system can aid in the early and prompt diagnosis of diseases. This paper used the stationary wavelet transform (SWT) for pre-processing the raw ECG signals and implemented recurrent neural networks (RNN), gated recurrent units (GRU), and bi-directional long short-term memory (Bi-LSTM) for beat classification. Among the three models, the Bi-LSTM network achieved the highest accuracy of 99.72%, indicating its suitability for computer-aided diagnosis of heartbeats.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Biomedical
Jie Liu et al.
Summary: This study proposes a method for predicting fetal ARR based on arrhythmia, using multi-domain feature extraction technique and hierarchical extreme learning machine network. Experimental results demonstrate high sensitivity, specificity, precision, and accuracy of the proposed method.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
P. Gomathi et al.
Summary: In order to detect breast cancer more efficiently, a 4D U-Net segmentation method using digital infrared thermal imaging system is proposed in this research. The proposed approach utilizes digital infrared thermal images and applies pre-processing techniques, image segmentation with 4D U-Net, and optimization of weight parameters with Glowworm Swarm Optimization Algorithm. The performance of the proposed approach surpasses existing methods in terms of accuracy and precision.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Kapil Gupta et al.
Summary: Measurement of abnormal heartbeat rhythm of a fetus to detect arrhythmia is important for assessing the health status of the fetus. However, recording clean fetal-electrocardiogram (f-ECG) signals under free-living conditions presents operational difficulties. This study proposes a new learning system based on the S-transform to denoise the f-ECG signals and detect arrhythmic fetuses.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Biomedical
S. Abhishek et al.
Summary: This paper details the design of bi orthogonal wavelet filters and experiments them in the MIT database. The experiments show that the designed wavelets have better sparse representation in ECG records compared to commonly used wavelets. Additionally, the paper provides a brief overview of the fundamentals of Compressed Sensing and some state of the art methods in CS based on ECG reconstruction scenarios.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Saeed Reza Kheradpisheh et al.
Summary: BS4NN is a modification of the S4NN algorithm, utilizing binary-constrained weights and operating in the time domain with neuron spikes propagated sequentially. It demonstrated reasonable accuracies on the MNIST and Fashion-MNIST benchmarks, outperforming a simple BNN with the same architectures.
NEURAL PROCESSING LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Hamidreza Ghonchi et al.
Summary: Fetal electrocardiogram (FECG) signals contain important information about the conditions of the fetus during pregnancy. This study proposes a novel network architecture that combines attention mechanisms and deep learning models to accurately extract FECG signals from abdominal data.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Information Systems
Huruy Tesfai et al.
Summary: This study proposes a lightweight CNN model based on the ShuffleNet architecture for deploying deep neural networks on wearable mobile edge devices with limited resources. It utilizes a sliding window and novel encoding scheme to increase the number of classes and allow detection of multiple classes. Additionally, it explores a loss function suitable for imbalanced datasets.
Article
Engineering, Electrical & Electronic
George Georgoulas et al.
Summary: By analyzing the features of FHR data through dimensionality reduction, this study found high overlap between classes formed using solely umbilical cord pH information, suggesting limitations in the performance expectation of current pH-based systems and the need for alternative approaches to enhance computer-based decision support technologies.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Katerina Barnova et al.
Summary: This study identified an effective method for extracting non-invasive fetal electrocardiogram (NI-fECG) from signals recorded from the mother's abdomen, combining independent component analysis (ICA), fast transversal filter (FTF), and complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Testing on two patient databases demonstrated that this combined method is capable of accurately extracting fECG with lower computational complexity.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Biomedical
Abel Jaba Deva Krupa et al.
Summary: This paper introduces a novel algorithm combining fractional Fourier transform and wavelet analysis to effectively extract fetal ECG from abdominal signals and accurately estimate fetal heart rate. The proposed approach achieves high accuracy, sensitivity, positive predictive value, and F1 measure, demonstrating its promising potential for FECG extraction.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Hongpo Zhang et al.
Summary: The study proposed a method using a simple deterministic measurement matrix for random projection operation on ECG signals to complete compression, followed by transpose projection operation on the compressed signals in the cloud to obtain approximate signals. By verifying the similarity between the approximate ECG signal and the original ECG signal, the effectiveness of compressed ECG signals in AF detection was explained. The TP-CNN was used to effectively detect AF on the obtained approximate ECG signals, showing promising results for AF detection in wearable application scenarios.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Computer Science, Theory & Methods
Bin Pu et al.
Summary: The article introduces a deep-learning hybrid framework for automatic detection of fetal echocardiograms, utilizing class score to locate end-systolic and end-diastolic frames. The framework integrates target detection, temporal dependency module, and classification module based on a domain-transferred deep convolutional neural network. Various CNN architectures and channel fusion strategies are explored, resulting in high accuracy of classification and minimal detection errors.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Engineering, Biomedical
Saurav Mandal et al.
Summary: The study aims to design a CAD system for classifying ECG signals of VT and VF patients, proposing a technique for cardiac scoring. Feature extraction methods are used for computing features from HRV signals and ECG beat images, with the best classification accuracy achieved by an ensemble classifier. The system can operate with a 99.99% accuracy rate for distinguishing between healthy individuals and those with VA.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Information Systems
Yu-Ching Ting et al.
Summary: A CNN-based approach is proposed for fetal ECG detection, achieving high detection accuracy through preprocessing and classification phases. The hardware implementation on the FPGA platform reduces latency of large-size convolution with a pre-fetch mechanism. Results show lower power consumption during real-time operations.
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Emerson Keenan et al.
Summary: This study presents an open-source method for modeling maternal body structure and fetal position changes in noninvasive fetal electrocardiography, with validation on specific fetal heart monitoring tasks and application in clinical scenarios.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Theory & Methods
Majid Akhavan-Amjadi
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Engineering, Biomedical
Y. S. Alshebly et al.
Article
Acoustics
Wafaa Alsaggaf et al.
Article
Multidisciplinary Sciences
Mohammad Dehghani et al.
SN APPLIED SCIENCES
(2020)
Article
Genetics & Heredity
Joachim A. Behar et al.
PRENATAL DIAGNOSIS
(2019)
