|
|
|
|
LEADER |
02651nam a2200421Ia 4500 |
001 |
10.3390-s22093303 |
008 |
220510s2022 CNT 000 0 und d |
020 |
|
|
|a 14248220 (ISSN)
|
245 |
1 |
0 |
|a A Deep Learning Approach for the Assessment of Signal Quality of Non-Invasive Foetal Electrocardiography
|
260 |
|
0 |
|b MDPI
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.3390/s22093303
|
520 |
3 |
|
|a Non-invasive foetal electrocardiography (NI-FECG) has become an important prenatal monitoring method in the hospital. However, due to its susceptibility to non-stationary noise sources and lack of robust extraction methods, the capture of high-quality NI-FECG remains a challenge. Recording waveforms of sufficient quality for clinical use typically requires human visual inspection of each recording. A Signal Quality Index (SQI) can help to automate this task but, contrary to adult ECG, work on SQIs for NI-FECG is sparse. In this paper, a multi-channel signal quality classifier for NI-FECG waveforms is presented. The model can be used during the capture of NI-FECG to assist technicians to record high-quality waveforms, which is currently a labour-intensive task. A Convolutional Neural Network (CNN) is trained to distinguish between NI-FECG segments of high and low quality. NI-FECG recordings with one maternal channel and three abdominal channels were collected from 100 subjects during a routine hospital screening (102.6 min of data). The model achieves an average 10-fold cross-validated AUC of 0.95 ± 0.02. The results show that the model can reliably assess the FECG signal quality on our dataset. The proposed model can improve the automated capture and analysis of NI-FECG as well as reduce technician labour time. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
|
650 |
0 |
4 |
|a Biomedical signal processing
|
650 |
0 |
4 |
|a Convolution
|
650 |
0 |
4 |
|a convolutional neural network
|
650 |
0 |
4 |
|a Convolutional neural network
|
650 |
0 |
4 |
|a Convolutional neural networks
|
650 |
0 |
4 |
|a Deep learning
|
650 |
0 |
4 |
|a Electrocardiography
|
650 |
0 |
4 |
|a Fetal ECG
|
650 |
0 |
4 |
|a Fetal electrocardiographies
|
650 |
0 |
4 |
|a foetal ECG
|
650 |
0 |
4 |
|a High quality
|
650 |
0 |
4 |
|a Hospitals
|
650 |
0 |
4 |
|a Learning approach
|
650 |
0 |
4 |
|a Monitoring methods
|
650 |
0 |
4 |
|a Noise source
|
650 |
0 |
4 |
|a Nonstationary noise
|
650 |
0 |
4 |
|a signal quality
|
650 |
0 |
4 |
|a Signal quality
|
650 |
0 |
4 |
|a Waveforms
|
700 |
1 |
|
|a Clifton, D.A.
|e author
|
700 |
1 |
|
|a Li, Y.
|e author
|
700 |
1 |
|
|a Liu, Z.
|e author
|
700 |
1 |
|
|a Long, Y.
|e author
|
700 |
1 |
|
|a Mertes, G.
|e author
|
700 |
1 |
|
|a Yang, Y.
|e author
|
773 |
|
|
|t Sensors
|