Remote vital parameter monitoring in neonatology – robust, unobtrusive heart rate detection in a realistic clinical scenario

Blanik, Nikolai; Heimann, Konrad; Pereira, Carina Barbosa; Paul, Michael; Blažek, Vladimír; Venema, Boudewijn; Orlikowsky, Thorsten; Leonhardt, Steffen

doi:10.1515/bmt-2016-0025

Cited by 27 publications

(28 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As of today, present results are based on relatively small datasets that range from seven [ 8 ] to 30 [ 9 ] different subjects. The videos were recorded either through the incubator glass [ 8 , 10 – 12 ], directly with open incubators [ 13 ], or through a specially drilled hole in a closed incubator [ 9 , 14 ]. Some dataset’s recordings comprise the majority of the infant’s body, whose skin is partially or not covered [ 14 ], while others apply zoom to focus specific uncovered body parts [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

“…Maintaining the circadian rhythm of neonates is of major concern in the neonatal intensive care unit (NICU). Thus, when deploying PPGI technology in such an environment, the usage of invisible near infrared (NIR) illumination is desirable [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

“…However, having a color-based skin classifier, where the ROI is not associated with the anatomical structure of interest, leads to non-robust vital parameter extraction in continuous monitoring over extended periods of time, as the author states in his conclusions. Blanik et al [ 10 ] opted to divide the video frames into squares of 30 pixels edge length and compute a quality index (QI) for each one. All the squares possessing a QI above a threshold of 90% of the maximum QI value will belong to the ROI and, consequently, will be used for HR estimation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast body part segmentation and tracking of neonatal video data using deep learning

Antink

Ferreira

Paul

et al. 2020

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

Photoplethysmography imaging (PPGI) for non-contact monitoring of preterm infants in the neonatal intensive care unit (NICU) is a promising technology, as it could reduce medical adhesive-related skin injuries and associated complications. For practical implementations of PPGI, a region of interest has to be detected automatically in real time. As the neonates’ body proportions differ significantly from adults, existing approaches may not be used in a straightforward way, and color-based skin detection requires RGB data, thus prohibiting the use of less-intrusive near-infrared (NIR) acquisition. In this paper, we present a deep learning-based method for segmentation of neonatal video data. We augmented an existing encoder-decoder semantic segmentation method with a modified version of the ResNet-50 encoder. This reduced the computational time by a factor of 7.5, so that 30 frames per second can be processed at 960 × 576 pixels. The method was developed and optimized on publicly available databases with segmentation data from adults. For evaluation, a comprehensive dataset consisting of RGB and NIR video recordings from 29 neonates with various skin tones recorded in two NICUs in Germany and India was used. From all recordings, 643 frames were manually segmented. After pre-training the model on the public adult data, parts of the neonatal data were used for additional learning and left-out neonates are used for cross-validated evaluation. On the RGB data, the head is segmented well (82% intersection over union, 88% accuracy), and performance is comparable with those achieved on large, public, non-neonatal datasets. On the other hand, performance on the NIR data was inferior. By employing data augmentation to generate additional virtual NIR data for training, results could be improved and the head could be segmented with 62% intersection over union and 65% accuracy. The method is in theory capable of performing segmentation in real time and thus it may provide a useful tool for future PPGI applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast body part segmentation and tracking of neonatal video data using deep learning

Antink

Ferreira

Paul

et al. 2020

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…It may also decrease the risk of limb ischemia and skin lesions due to electrode-related irritation and, thus, the risk of skin infections with subsequent use of antibiotics and disinfectants, which can alter the cerebral pressure and perfusion when inhaled (Blanik et al, 2016;Zhao et al, 2016;Cobos-Torres et al, 2018). ECG alternatives to monitor HRV are paramount since, due to altered evaporation of body water, electrodes on large skin areas may influence the balance between heat and water in preterm newborns who weigh less than 1,000 g (Blanik et al, 2016). Avoiding electrodes would also reduce the workload of NICU professionals since they might avoid controlling the correct positioning of patches (Cobos-Torres et al, 2018).…”

Section: The Current State Of Hrv Assessment and Limitationsmentioning

confidence: 99%

Heart Rate Variability in the Perinatal Period: A Critical and Conceptual Review

Chiera¹,

Cerritelli²,

Casini³

et al. 2020

Front. Neurosci.

View full text Add to dashboard Cite

Neonatal intensive care units (NICUs) greatly expand the use of technology. There is a need to accurately diagnose discomfort, pain, and complications, such as sepsis, mainly before they occur. While specific treatments are possible, they are often timeconsuming, invasive, or painful, with detrimental effects for the development of the infant. In the last 40 years, heart rate variability (HRV) has emerged as a noninvasive measurement to monitor newborns and infants, but it still is underused. Hence, the present paper aims to review the utility of HRV in neonatology and the instruments available to assess it, showing how HRV could be an innovative tool in the years to come. When continuously monitored, HRV could help assess the baby's overall wellbeing and neurological development to detect stress-/painrelated behaviors or pathological conditions, such as respiratory distress syndrome and hyperbilirubinemia, to address when to perform procedures to reduce the baby's stress/pain and interventions, such as therapeutic hypothermia, and to avoid severe complications, such as sepsis and necrotizing enterocolitis, thus reducing mortality. Based on literature and previous experiences, the first step to efficiently introduce HRV in the NICUs could consist in a monitoring system that uses photoplethysmography, which is low-cost and non-invasive, and displays one or a few metrics with good clinical utility. However, to fully harness HRV clinical potential and to greatly improve neonatal care, the monitoring systems will have to rely on modern bioinformatics (machine learning and artificial intelligence algorithms), which could easily integrate infant's HRV metrics, vital signs, and especially past history, thus elaborating models capable to efficiently monitor and predict the infant's clinical conditions. For this reason, hospitals and institutions will have to establish tight collaborations between the obstetric, neonatal, and pediatric departments: this way, healthcare would truly improve in every stage of the perinatal period (from conception to the first years of life), since information about patients' health would flow freely among different professionals, and high-quality research could be performed integrating the data recorded in those departments.

show abstract

“…There have been increasing demands for unobtrusive and contactless, as well as reliable and feasible, monitoring techniques to improve patients’ quality of life and optimize the use of medical resources [ 6 ]. Examples of new monitoring solutions that have been tested and proposed include: Doppler radar [ 6 ], capacitive electrocardiography (cECG) [ 7 ], magnetic induction [ 8 ], and imaging sensors, e.g., visible/near-infrared [ 2 , 9 , 10 , 11 ], mid-wave infrared (MWIR) [ 3 , 12 ] and long-wave infrared (LWIR) imaging sensors [ 3 , 13 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Monitoring of Cardiorespiratory Signals Using Thermal Imaging: A Pilot Study on Healthy Human Subjects

Pereira

Czaplik

Blažek

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Heart rate (HR) and respiratory rate (RR) are important parameters for patient assessment. However, current measurement techniques require attachment of sensors to the patient’s body, often leading to discomfort, stress and even pain. A new algorithm is presented for monitoring both HR and RR using thermal imaging. The cyclical ejection of blood flow from the heart to the head (through carotid arteries and thoracic aorta) leads to periodic movements of the head; these vertical movements are used to assess HR. Respiratory rate is estimated by using temperature fluctuations under the nose during the respiratory cycle. To test the viability and feasibility of this approach, a pilot study was conducted with 20 healthy subjects (aged 18–36 and 1 aged 50 years). The study consisted of two phases: phase A (frontal view acquisitions) and phase B (side view acquisitions). To validate the results, photoplethysmography and thoracic effort (piezoplethysmography) were simultaneously recorded. High agreement between infrared thermography and ground truth/gold standard was achieved. For HR, the root-mean-square errors (RMSE) for phases A and B were 3.53 ± 1.53 and 3.43 ± 1.61 beats per minute, respectively. For RR, the RMSE between thermal imaging and piezoplethysmography stayed around 0.71 ± 0.30 breaths per minute (phase A). This study demonstrates that infrared thermography may be a promising, clinically relevant alternative for the assessment of HR and RR.

show abstract

Remote vital parameter monitoring in neonatology – robust, unobtrusive heart rate detection in a realistic clinical scenario

Cited by 27 publications

References 18 publications

Fast body part segmentation and tracking of neonatal video data using deep learning

Fast body part segmentation and tracking of neonatal video data using deep learning

Heart Rate Variability in the Perinatal Period: A Critical and Conceptual Review

Monitoring of Cardiorespiratory Signals Using Thermal Imaging: A Pilot Study on Healthy Human Subjects

Contact Info

Product

Resources

About