Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Pulse Oximetry01:24

Pulse Oximetry

Pulse oximetry, or SpO2, is a non-invasive method for continuously monitoring arterial oxygen saturation (SaO2). This procedure involves attaching a probe or sensor to the patient's fingertip, forehead, earlobe, or nose bridge. The sensor works by detecting changes in oxygen saturation levels through light signals generated by the oximeter and reflected by the pulsing blood under the probe.
Purpose
Average SpO2 values are greater than 95%. If the readings fall below 90%, it indicates that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Reliability and reproducibility of piezoelectric-derived local brachial pulse wave velocity measurement and pressure normalization.

Biomedical physics & engineering express·2026
Same author

CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training.

Neuroinformatics·2026
Same author

AD-DAE: Alzheimer's Disease Progression Modeling with Unpaired Longitudinal MRI using Diffusion Auto-Encoders.

IEEE journal of biomedical and health informatics·2026
Same author

An Image-Free Ultrasound-Based Approach for Combined Assessment of Local and Regional Arterial Stiffness in Humans.

Journal of visualized experiments : JoVE·2026
Same author

Deep Learning-Based Cardiac Output Estimation Using Multimodal Physiological Signals.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Unobtrusive Heart Rate Variability Monitoring with a Chair-Based Strain Gauge Ballistocardiography in Office and Home Settings.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

Related Experiment Video

Updated: Jun 15, 2026

Neonatal Pial Surface Electroporation
06:22

Neonatal Pial Surface Electroporation

Published on: May 7, 2014

14.0K

Vision Transformer and NeoPulseNet: A Dual Approach for Accurate rPPG Signal Extraction in Neonates.

Aravind A Anil, Srinivasa Karthik, Mohanasankar Sivaprakasam

    IEEE Journal of Biomedical and Health Informatics
    |August 22, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces NeoPulseNet for non-contact neonatal heart rate (HR) monitoring. The AI model accurately segments infant skin and extracts HR, achieving clinically acceptable accuracy even in challenging conditions.

    More Related Videos

    Transcutaneous Microcirculatory Imaging in Preterm Neonates
    06:27

    Transcutaneous Microcirculatory Imaging in Preterm Neonates

    Published on: December 31, 2015

    8.3K
    How to Obtain Reliable Visual Event-related Potentials in Newborns
    07:39

    How to Obtain Reliable Visual Event-related Potentials in Newborns

    Published on: October 24, 2019

    6.5K

    Related Experiment Videos

    Last Updated: Jun 15, 2026

    Neonatal Pial Surface Electroporation
    06:22

    Neonatal Pial Surface Electroporation

    Published on: May 7, 2014

    14.0K
    Transcutaneous Microcirculatory Imaging in Preterm Neonates
    06:27

    Transcutaneous Microcirculatory Imaging in Preterm Neonates

    Published on: December 31, 2015

    8.3K
    How to Obtain Reliable Visual Event-related Potentials in Newborns
    07:39

    How to Obtain Reliable Visual Event-related Potentials in Newborns

    Published on: October 24, 2019

    6.5K

    Area of Science:

    • Biomedical Engineering
    • Medical Imaging
    • Artificial Intelligence

    Background:

    • Non-contact photoplethysmography (rPPG) offers a safer alternative for neonatal heart rate (HR) monitoring.
    • Accurate skin segmentation on neonates is challenging due to caregiver interference.

    Purpose of the Study:

    • To develop and validate an AI-based system for non-contact neonatal HR monitoring.
    • To improve the accuracy and robustness of rPPG in neonatal intensive care settings.

    Main Methods:

    • A vision transformer was used for neonatal skin segmentation.
    • A novel deep learning architecture, NeoPulseNet (1D-CNNs and transformer layers), was developed for HR extraction using surrogate ground truth.
    • Performance was evaluated against traditional rPPG algorithms and validated under diverse neonatal conditions.

    Main Results:

    • NeoPulseNet achieved a mean absolute error (MAE) as low as 7.85 bpm by optimizing surrogate ground truth.
    • The model demonstrated consistent clinical acceptability (MAE ≤ 10 bpm) across variations in skin tone, position, lighting, and motion.
    • NeoPulseNet exhibited efficient computation (13 ms on 5-second segments), comparable to classical methods.

    Conclusions:

    • NeoPulseNet provides a robust and computationally efficient solution for non-contact neonatal HR monitoring.
    • AI-driven rPPG, particularly with surrogate training, significantly enhances accuracy over traditional methods in neonates.
    • The system shows promise for clinical application in neonatal care, improving safety and data acquisition.