ECG Waveforms Reconstruction based on Equivalent Time Sampling

Fiori, Giorgia; Scorza, Andrea; Conforto, Silvia; Fuiano, Fabio; Schmid, Maurizio; Sciuto, Salvatore Andrea

doi:10.1109/memea49120.2020.9137260

Cited by 7 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ECG data sets can be treated more to QRS complex detection. Numerous parameters can be extracted from the ECG signals for instance random data series analysis, including Gaussian noise [24,25], random transient pulses [26] or train of random pulse spikes [27]. The QRS complex advantages are presented in the implementation simplicity and reducing computational time.…”

Section: Resultsmentioning

confidence: 99%

ConvNet: 1D-Convolutional Neural Networks for Cardiac Arrhythmia Recognition Using ECG Signals

Slama¹,

Sahli²,

Maalmi³

et al. 2021

View full text Add to dashboard Cite

In healthcare, diagnostic tools of cardiac diseases are commonly known by the electrocardiogram (ECG) analysis. Atypical electrical activity can produce a cardiac arrhythmia. Various difficulties can be imposed to clinicians e.g., myocardial infarction arrhythmia via the non-stationarity and irregularity heart beat signals. Through the assistance of computer-aided diagnosis methods, timely specification of arrhythmia diseases reduces the mortality rate of affected patients. In this study, a 1 Lead QRS complex -layer deep convolutional neural network is proposed for the recognition of arrhythmia datasets. By the use of this CNN model, we planned a complete structure of the classification architecture after a pre-processing stage counting the denoising and QRS complex signals detection procedure. The chief benefit of the new proposed methodology is that the automatically training the QRS complexes without requiring all original extracted ECG signals. The proposed model was trained on the increased ECG database and separated into five classes. Experimental results display that the established CNN method has improved performance when compared to the state-of-the-art studies.

show abstract

Section: Resultsmentioning

confidence: 99%

ConvNet: 1D-Convolutional Neural Networks for Cardiac Arrhythmia Recognition Using ECG Signals

Slama¹,

Sahli²,

Maalmi³

et al. 2021

View full text Add to dashboard Cite

show abstract

“…An uncertainty analysis was also conducted based on the main sources of error, these included the uncertainty on the pixel resolution of the CT images, while the uncertainty of the measurement image analysis was evaluated by a Monte Carlo simulation [23][24][25][26] with 10 4 iterations where the grey level threshold value for the mask of the replicas was made to vary randomly through a uniform distribution with ± 5% bounds. For a first estimation of the overall measurement uncertainty, shown in Table 3 and in Table 4, the above two uncertainty contributions were combined together by applying the uncertainty propagation law.…”

Section: Ct Parameter Settingmentioning

confidence: 99%

Dimensional assessment in bioarchaeology applications: a preliminary study on quality controls in 3D printing of human skulls

Cecchitelli,

Fiori,

Bocchetta

et al. 2023

Proceedings of the 2022 IMEKO TC4 International Conference on Metrology for Archaeology and Cultural Heritage

View full text Add to dashboard Cite

In the last few years, three-dimensional (3D) printing has been used in archaeology and cultural heritage fields for different purposes. Among the different technologies of 3D printing, e.g., stereolithography or selective laser sintering, this study focuses on the quality assessment of printed models using fused deposition modeling technology. To simulate archaeological human remains, a cranial model assumed as a gold standard has been printed from computed tomography (CT) data of a human skull. Eight 3D printed (3DP) models have been reproduced and CT scanned with the same protocol in order to quantify their congruence with the gold standard through an objective measurement method based on image analysis. Preliminary results show an increasing percentage error as the degree of model detail increases, from 1% to 15%. The experimental results are discussed and commented also from a metrological point of view.

show abstract

“…Color Doppler data were collected through a US diagnostic system equipped with a phased array probe, whose main settings are listed in Table 2. Based on [36], a Doppler video lasting 140 s was acquired for each phantom frequency and flow regime and postprocessed by ETiSIAM for PTT estimation. Then, FAV value was assessed and compared with the corresponding preset value.…”

Section: Parameter Characteristicmentioning

confidence: 99%

“…ETiSIAM was developed starting from a previous study [36], in which ETS was applied to electrophysiological signals. As already described in [36], ETS relies on a trigger event to collect samples.…”

Section: Signal Triggeringmentioning

confidence: 99%

“…Up to now, ETS has been applied in the biomedical field as a sampling technique in the pre-acquisition phase [34,35] and it seems that it has rarely been used as a post-processing tool. To the authors' knowledge, just a single study proposing a first approach for the ETS reconstruction of the electrocardiographic signals in the post-processing phase has been carried out [36]. The novelty of the present study is the ETS post-processing application to CD videos acquired from two different experimental setups, to demonstrate its potentiality in the US diagnostic field for the assessment of both FAV and PWV, according to the characteristics of the test object under investigation and overcoming the bandwidth limitations of the ultrasound system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Equivalent Time Sampling-Based Method for Pulse Transit Time Estimation with Applications into the Cardiovascular Disease Diagnosis

Fiori

Fuiano

Conforto

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The increasing incidence of cardiovascular diseases (CVDs) is reflected in additional costs for healthcare systems all over the world. To date, pulse transit time (PTT) is considered a key index of cardiovascular health status and for diagnosis of CVDs. In this context, the present study focuses on a novel image analysis-based method for PTT estimation through the application of equivalent time sampling. The method, which post-processes color Doppler videos, was tested on two different setups: a Doppler flow phantom set in pulsatile mode and an in-house arterial simulator. In the former, the Doppler shift was due to the echogenic properties of the blood mimicking fluid only, since the phantom vessels are non-compliant. In the latter, the Doppler signal relied on the wall movement of compliant vessels in which a fluid with low echogenic properties was pumped. Therefore, the two setups allowed the measurement of the flow average velocity (FAV) and the pulse wave velocity (PWV), respectively. Data were collected through an ultrasound diagnostic system equipped with a phased array probe. Experimental outcomes confirm that the proposed method can represent an alternative tool for the local measurement of both FAV in non-compliant vessels and PWV in compliant vessels filled with low echogenic fluids.

show abstract

ECG Waveforms Reconstruction based on Equivalent Time Sampling

Cited by 7 publications

References 18 publications

ConvNet: 1D-Convolutional Neural Networks for Cardiac Arrhythmia Recognition Using ECG Signals

ConvNet: 1D-Convolutional Neural Networks for Cardiac Arrhythmia Recognition Using ECG Signals

Dimensional assessment in bioarchaeology applications: a preliminary study on quality controls in 3D printing of human skulls

A Novel Equivalent Time Sampling-Based Method for Pulse Transit Time Estimation with Applications into the Cardiovascular Disease Diagnosis

Contact Info

Product

Resources

About