Medical diagnosis of the cardiovascular system on the carotid artery with IR laser Doppler vibrometer

Mignanelli, Laura; Rembe, Christian; Kroschel, Kristian; Luik, Armin; Castellini, Paolo; Scalise, Lorenzo

doi:10.1063/1.4879597

Cited by 7 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the two windows in the LDV (i.e., those corresponding to the R and T peaks in the ECG) shared a similar waveform. The similar waveform may be attributed to the contribution of the blood passage in the jugular vein [ 26 ]. Nonetheless, despite the probability being larger than 50%, it is worth noticing that the probability for the heartbeat window was always larger than 80%.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Antognoli

Moccia

Migliorelli

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Background: Heartbeat detection is a crucial step in several clinical fields. Laser Doppler Vibrometer (LDV) is a promising non-contact measurement for heartbeat detection. The aim of this work is to assess whether machine learning can be used for detecting heartbeat from the carotid LDV signal. Methods: The performances of Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (KNN) were compared using the leave-one-subject-out cross-validation as the testing protocol in an LDV dataset collected from 28 subjects. The classification was conducted on LDV signal windows, which were labeled as beat, if containing a beat, or no-beat, otherwise. The labeling procedure was performed using electrocardiography as the gold standard. Results: For the beat class, the f1-score (f1) values were 0.93, 0.93, 0.95, 0.96 for RF, DT, KNN and SVM, respectively. No statistical differences were found between the classifiers. When testing the SVM on the full-length (10 min long) LDV signals, to simulate a real-world application, we achieved a median macro-f1 of 0.76. Conclusions: Using machine learning for heartbeat detection from carotid LDV signals showed encouraging results, representing a promising step in the field of contactless cardiovascular signal analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The maximum peak amplitude is found in proximity of the carotid, detected by palpation. In [ 26 ], a study is performed to understand how the blood passage in the jugular may affect the LDV measurement related to the carotid artery. To this goal, an ultrasonic doppler is used.…”

Section: Introductionmentioning

confidence: 99%

Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Antognoli

Moccia

Migliorelli

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…A possible use case is medical applications, where LDVs are used for contactless measurements, such as monitoring cardiovascular activity [ 5 , 23 ]. In such cases, it is not always possible to guarantee sufficient reflectivity of the skin and that the patient does not move, or the appropriate procedures involved in ensuring this require greater effort [ 23 ].…”

Section: Discussionmentioning

confidence: 99%

“…With the advancement of laser-Doppler vibrometers (LDVs), various additional applications are continuously made available in which contactless vibration measurement is possible [1][2][3]. These applications are difficult to implement with conventional methods of vibration measurement, impossible in the case of rotating or hot parts [4], or unwanted in medical applications [5].…”

Section: Introductionmentioning

confidence: 99%

Signal Diversity for Laser-Doppler Vibrometers with Raw-Signal Combination

Schewe

Rembe

2021

Sensors

Self Cite

View full text Add to dashboard Cite

The intensity of the reflected measuring beam is greatly reduced for laser-Doppler vibrometer (LDV) measurements on rough surfaces since a considerable part of the light is scattered and cannot reach the photodetector (laser speckle effect). The low intensity of the reflected laser beam leads to a so-called signal dropout, which manifests as noise peaks in the demodulated velocity signal. In such cases, no light reaches the detector at a specific time and, therefore, no signal can be detected. Consequently, the overall quality of the signal decreases significantly. In the literature, first attempts and a practical implementation to reduce this effect by signal diversity can be found. In this article, a practical implementation with four measuring heads of a Multipoint Vibrometer (MPV) and an evaluation and optimization of an algorithm from the literature is presented. The limitations of the algorithm, which combines velocity signals, are shown by evaluating our measurements. We present a modified algorithm, which generates a combined detector signal from the raw signals of the individual channels, reducing the mean noise level in our measurement by more than 10 dB. By comparing the results of our new algorithm with the algorithms of the state-of-the-art, we can show an improvement of the noise reduction with our approach.

show abstract

“…This is not surprising-as a possible limitation of the technique-LDV is very sensitive to all kinds of velocity components contributing to the assessed skin surface. These components can originate from breathing and other involuntary muscle contractions, pulsations from nearby arteries and even veins (Mignanelli et al 2014), and vibrations from the building and the measurement setup itself. We kept the rejection procedures for data quite strict to account for the variability in the biological samples and the many artifacts from aforementioned sources, such that most DN values were rejected.…”

Section: Discrepancies With Previous Observationsmentioning

confidence: 99%

A non-contact approach for PWV detection: application in a clinical setting

et al. 2016

View full text Add to dashboard Cite

A need for screening methods for arteriosclerosis led to the development of several approaches to measure pulse wave velocity (PWV) being indicative of arterial stiffness. Carotid-femoral PWV (cfPWV) can be measured between common carotid artery (CCA) and femoral artery (FA) displaying the physiologically important stiffness of the conduit arteries. However, this measurement approach has several disadvantages, and a local PWV-measurement of CCA-stiffness has been proposed as an alternative in the past. In the presented pilot study, laser Doppler vibrometry (LDV) is used to measure PWV locally in the CCA (PWVLDV) in 48 patients aged between 48 and 70, with known atherosclerotic arterial disease: stabilized coronary artery disease (CAD), cerebro-vascular disease (CVD) or peripheral artery disease (PAD). Additionally, cfPWV, CCA distensibility coefficient (DC), CCA intima-media thickness (IMT), blood pressure (BP) and age were evaluated. LDV is a valid method for local PWV-measurement. The method is potentially easy to use, and causes no discomfort to the patient. PWVLDV correlates with age (R = 0.432; p = 0.002) as reported in related studies using other techniques, and measured values lay between 2.5 and 5.8 m s(-1), which is well in line with literature measures of local PWV in the CCA. In conclusion, PWVLDV potentially is a marker for arterial health, but more research in a larger and more homogeneous patient population is mandatory. In future studies, blood velocity measurements should be incorporated, as well as a reference method such as pulse wave imaging (PWI) or magnetic resonance imaging (MRI).

show abstract

Medical diagnosis of the cardiovascular system on the carotid artery with IR laser Doppler vibrometer

Cited by 7 publications

References 0 publications

Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

Signal Diversity for Laser-Doppler Vibrometers with Raw-Signal Combination

A non-contact approach for PWV detection: application in a clinical setting

Contact Info

Product

Resources

About