iPPG 2 cPPG: Reconstructing contact from imaging photoplethysmographic signals using U-Net architectures

Autor: Alain Pruski, Djamaleddine Djeldjli, Choubeila Maaoui, Frédéric Bousefsaf, Yassine Ouzar
Přispěvatelé: Laboratoire de Conception, Optimisation et Modélisation des Systèmes (LCOMS), Université de Lorraine (UL)
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Diagnostic Imaging
Computer science
[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging
Blood Pressure
Health Informatics
02 engineering and technology
Blood volume pulse
01 natural sciences
Pulse waveform
Respiratory Rate
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing
Heart Rate
Photoplethysmogram
Limit (music)
Waveform
Photoplethysmography
Continuous wavelet transform
blood volume pulse
business.industry
010401 analytical chemistry
Estimator
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Blood Pressure Determination
Signal Processing
Computer-Assisted

Pattern recognition
021001 nanoscience & nanotechnology
U-Net
0104 chemical sciences
Computer Science Applications
Artificial intelligence
0210 nano-technology
Focus (optics)
business
imaging photoplethysmography
Zdroj: Computers in Biology and Medicine
Computers in Biology and Medicine, Elsevier, 2021, 138, pp.104860. ⟨10.1016/j.compbiomed.2021.104860⟩
ISSN: 0010-4825
DOI: 10.1016/j.compbiomed.2021.104860⟩
Popis: International audience; Imaging photoplethysmography (iPPG) is an optical technique dedicated to the assessment of several vital functions using a simple camera. Signicant eorts have been made to reliably estimate heart and respiratory rates. Currently, research is focusing on the remote estimation of oxygen saturation and blood pressure (BP). The limited number of publicly available data tends to restrict the advancements related to BP estimation. To overcome this limit, we propose to split the problem in a two-stage processing chain: (i) converting iPPG to contact PPG (cPPG) signals using available video dataset and (ii) estimate BP from converted cPPG signals by exploiting large existing databases (e.g. MIMIC). This article presents the rst developments where a method for converting iPPG signals measured using a camera into cPPG signals measured by contact sensors is proposed. Real and imaginary parts of the continuous wavelet transform (CWT) of cPPG and iPPG signals are passed to various deep pre-trained U-shaped architectures. Conventional metrics and specic waveform estimators have been implemented to validate the relevance of the predictions. The results exhibit good agreements towards a large portion of metrics, showing that the neural architectures properly estimated cPPG from iPPG signals through their CWT representations. The performance indicates that BP estimation from iPPG signals converted to cPPG signals can now be envisaged. Consequently, future work will focus on the integration of models dedicated to BP estimation trained on MIMIC. This is the rst demonstration of a method for accurate reconstruction of cPPG from iPPG signals satisfying pulse waveform criteria.
Databáze: OpenAIRE