Next Article in Journal
Quantitative Evaluation of Burn Injuries Based on Electrical Impedance Spectroscopy of Blood with a Seven-Parameter Equivalent Circuit
Previous Article in Journal
Optimization of Mixed Numerology Profiles for 5G Wireless Communication Scenarios
Previous Article in Special Issue
SDNN24 Estimation from Semi-Continuous HR Measures
Open AccessArticle

A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients

1
Medical Information Technology, Helmholtz Institute for Biomedical Engineering, RWTH Aachen University, 52074 Aachen, Germany
2
Eastern Health Clinical School, Monash University Melbourne, Box Hill, VIC 3128, Australia
3
Research Centre for Musculoskeletal Science and Sports Medicine, Manchester Metropolitan University, Manchester M1 5GD, UK
4
Biomedical Engineering, Electrical Engineering and Information Technology, TU Darmstadt, 64289 Darmstadt, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Jari Viik
Sensors 2021, 21(4), 1495; https://doi.org/10.3390/s21041495
Received: 3 December 2020 / Revised: 11 February 2021 / Accepted: 16 February 2021 / Published: 21 February 2021
Infrared thermography for camera-based skin temperature measurement is increasingly used in medical practice, e.g., to detect fevers and infections, such as recently in the COVID-19 pandemic. This contactless method is a promising technology to continuously monitor the vital signs of patients in clinical environments. In this study, we investigated both skin temperature trend measurement and the extraction of respiration-related chest movements to determine the respiratory rate using low-cost hardware in combination with advanced algorithms. In addition, the frequency of medical examinations or visits to the patients was extracted. We implemented a deep learning-based algorithm for real-time vital sign extraction from thermography images. A clinical trial was conducted to record data from patients on an intensive care unit. The YOLOv4-Tiny object detector was applied to extract image regions containing vital signs (head and chest). The infrared frames were manually labeled for evaluation. Validation was performed on a hold-out test dataset of 6 patients and revealed good detector performance (0.75 intersection over union, 0.94 mean average precision). An optical flow algorithm was used to extract the respiratory rate from the chest region. The results show a mean absolute error of 2.69 bpm. We observed a computational performance of 47 fps on an NVIDIA Jetson Xavier NX module for YOLOv4-Tiny, which proves real-time capability on an embedded GPU system. In conclusion, the proposed method can perform real-time vital sign extraction on a low-cost system-on-module and may thus be a useful method for future contactless vital sign measurements. View Full-Text
Keywords: camera-based vital sign measurement; infrared thermography; IRT; object detection; deep learning; optical flow; ICU monitoring camera-based vital sign measurement; infrared thermography; IRT; object detection; deep learning; optical flow; ICU monitoring
Show Figures

Graphical abstract

MDPI and ACS Style

Lyra, S.; Mayer, L.; Ou, L.; Chen, D.; Timms, P.; Tay, A.; Chan, P.Y.; Ganse, B.; Leonhardt, S.; Hoog Antink, C. A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients. Sensors 2021, 21, 1495. https://doi.org/10.3390/s21041495

AMA Style

Lyra S, Mayer L, Ou L, Chen D, Timms P, Tay A, Chan PY, Ganse B, Leonhardt S, Hoog Antink C. A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients. Sensors. 2021; 21(4):1495. https://doi.org/10.3390/s21041495

Chicago/Turabian Style

Lyra, Simon; Mayer, Leon; Ou, Liyang; Chen, David; Timms, Paddy; Tay, Andrew; Chan, Peter Y.; Ganse, Bergita; Leonhardt, Steffen; Hoog Antink, Christoph. 2021. "A Deep Learning-Based Camera Approach for Vital Sign Monitoring Using Thermography Images for ICU Patients" Sensors 21, no. 4: 1495. https://doi.org/10.3390/s21041495

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop