Search

A data processing device (100, 200) is disclosed for extracting a desired vital signal containing a physiological information component from sensor data that includes time-dependent first sensor data (PPG1) comprising the physiological information component and at least one motion artifact component, and that includes time-dependent second sensor data that is indicative of a position, a velocity or an acceleration of the sensed region as a function of time. A decomposition unit (104, 204) decomposes the second sensor data into at least two components of decomposed sensor data and, based on the decomposed second sensor data, provides at least two different sets of motion reference data in at least two different motion reference data channels. An artifact removal unit (106, 206) determines the vital signal formed from a linear combination of the first sensor data and the motion reference data of at least one two of the motion reference data channels.

In an approach to obtaining vital signs of a subject, a subject monitoring device obtains at least two detection signals acquired from a subject that are related to a physiological property of the subject and allows extraction of a vital sign of the subject. The subject monitoring device performs a spectral decomposition of the at least two detection signals to obtain two or more spectral components of the detection signals and determines a weight per spectral component based on an estimate of the relevance. The subject monitoring device determines a weight value by determining at least one of a variance of the spectral component and a standard deviation of the spectral component and determines whether at least one of the variance and the standard deviation exceed a predetermined limit. Responsive to determining that at least one of the variance and the standard deviation do not exceed the predetermined limit, the subject monitoring device setts the weight to a weight value of 1 and extracts the weighted vital sign of the subject.

The present invention relates to a system and method for determining a vital sign of a subject. To improve the detection of electromagnetic radiation reflected from or transmitted through skin of a subject (110) at least two differently modulated radiation sources (112, 114) are used. For both camera and single-element sensors, this allows access (after demodulation) to different mixtures of skin and non-skin reflections/transmissions that can be de-mixed and successively allows the skin-only signal to be used for photo-plethysmography, PPG, extraction. Thus, a sensor (130) detects the reflected or transmitted electromagnetic radiation and a demodulation unit (140) and processing unit (150) enable to determine a vital sign (160) from said detection signal.

This invention provides a process which allows better quality rendering of video on any display. The process proposes encoding, video data and additional data. The additional data includes a change time instant. The change time instant can be used to indicate a change in time of a characteristic luminance. The characteristic luminance summarizes the set of luminances of pixels in an image of the video data. The process includes generating on descriptive data based on the video data and encoding and outputting the descriptive data as additional data.

The present invention relates to a device, system and a method for generating a photoplethysmographic image carrying vital sign information of a subject. To provide an increased validity and robustness against motion, in particular against ballistocardiographic motion, the proposed device comprises an input interface (30) for obtaining image data of a skin region of a subject in at least two different wavelength channels, said image data comprising two or more image frames acquired by detecting light transmitted through or reflected from the skin region over time, wherein said image data comprise wavelength-dependent reflection or transmission information in said at least two different wavelength channels, a combination unit (31) for combining, per pixel or group of pixels and per time instant, image data values of said at least two different wavelength channels to obtain a time-variant pulse signal per pixel or group …

The present invention relates to a device, system and method for image segmentation of an image of a scene including a subject. To improve the segmentation, the device comprises a receiver (210) configured to receive electromagnetic radiation reflected from a scene including a subject, a polarization unit (220) configured to apply a first polarization on the received electromagnetic radiation to generate first polarized radiation and to apply a second polarization, which is different from the first polarization, on the received electromagnetic radiation to generate second polarized radiation, a sensor unit (230) configured to generate a first image from the first polarized radiation and a second image from the second polarized radiation, and a segmentation unit (250) configured to identify areas of different materials in the scene from a combination of the first and second images. Further, a vital sign determination unit (240) is provided that is configured to select an area representing skin of the subject, to generate a first detection signal having a first polarization direction from the first polarized radiation in the selected area and a second detection signal having a second polarization direction, which is different from the first polarization direction, from the second polarized radiation in the selected area, and to determine a vital sign from the two detection signals by combining the two detection signals.

The present invention relates to a device, system and method for extracting physiological information indicative of at least one vital sign of a subject. To solve the motion robustness problem of known solutions, the device comprises a pre-treatment unit (210) configured to derive at least three detection signals from electromagnetic radiation reflected from a skin region of a subject, wherein at least two detection signals comprise wavelength-dependent reflection information in a different wavelength channel and at least two detection signals comprise reflection information in different polarization channels having different polarization directions. This provides that a channel that always has a low pulsatility, even when the SpO2 value is low. This channel mainly contains the motion-induced distortions. Adding this always low-pulsatile channel to the generally known PBV pulse extraction or the ABPV SpO2 measurement algorithm, or replacing an existing channel solves the reduced motion robustness problem of the known systems and methods.

The present invention relates to a system and method for determining at least one vital sign of a subject. To improve the ambient light robustness, said system comprises an illumination unit (2) configured to illuminate a skin region of the subject, said illumination unit comprising a first radiation source (20) and a second radiation source (21), which are configured to emit differently modulated electromagnetic radiation in two or more wavelength channels and/or in two or more polarization channels, a detection unit (4) configured to detect electromagnetic radiation reflected from the skin region of the subject and to generate detection signals, wherein the detection unit (4) comprises a plurality of detection elements and wherein a detection signal is generated per detection element or group of two or more detection elements, a processing unit (11) configured to demodulate the detection signals corresponding to the modulation applied by the illumination unit to obtain demodulated detection signals, and a vital signs determination unit (5) configured to determine, per wavelength or polarization channel, a statistical measure from said demodulated detection signals at the same instant of time and to extract a vital sign from said statistical measures.

The present invention relates to a device, system and method for less obtrusively determining a tissue characteristic of a subject, the device comprises a first control unit (11) configured to control an electromechanical transducer (31) by a first control signal (21) to transfer mechanical waves varying in a frequency range or with varying frequency content to an exposed tissue area of the subject; a second control unit (12) configured to control an electromagnetic radiation emitter (32) by a second control signal (22) to emit electromagnetic radiation towards the exposed tissue area of the subject; a radiation signal input (13) configured to obtain a radiation signal (23) indicative of electromagnetic radiation reflected from the exposed tissue area of the subject; and a processor (14) configured to determine a tissue characteristic signal (24) indicative of a tissue characteristic of the exposed tissue area of the subject derived …

The present invention relates to a device, system and method for determining a vital sign of a subject. To reduce the effects of subject motion, in particular of ballistocardiographic motion, the device comprises an input interface (30) for obtaining at least two radiation signals, each radiation signal being acquired from different skin regions of the subject by detecting radiation reflected from or transmitted through the respective skin region in response to irradiation, an extraction unit (31) for extracting photoplethysmography (PPG) signals from the obtained radiation signals to obtain at least one PPG signal per skin region, an evaluation unit (32) for determining first weights for said skin regions depending on the relative and/or absolute strength of fundamental frequency and/or one or more harmonics in the spectrum of the PPG signal of the respective skin region, a combination unit (33) for combining two or more PPG signals of different skin regions based on their respective first weights to obtain a combined PPG signal, and a vital sign determination unit (34) for deriving a vital sign from the combined PPG signal.

The present invention relates to a wearable device for acquiring physiological information of a subject. To combine the advantages of a contact sensor and a contactless sensor, the wearable device comprises an optical emitter (10) for emitting light into the subject's skin, an optical sensor (20) for receiving light scattered back from the subject's skin in response to the emission of light into the subject's skin, the received light representing or allowing the derivation of physiological information of the subject, and a carrier (30) for being held at the subject's skin and for carrying said emitter (10) and said sensor (20) such that a light receiving area (12), at which the emitted light enters the subject's skin, substantially corresponds to a light reflecting area (22), at which at least part of the scattered light leaves the subject's skin and is received by said optical sensor, the optical sensor (20) is arranged between the optical emitter (10) and the light receiving area (12) and is at least partially transparent for the light emitted by the optical emitter or the optical emitter (10) is arranged between the optical sensor (20) and the light reflecting area (22) and is at least partially transparent for the light reflected from the light reflecting area.

The present invention relates to a device, system and method for obtaining vital sign related information of a living being. The proposed device comprises an input unit for receiving an input signal generated from light received in at least one wavelength interval reflected from a skin region of a living being, said input signal representing vital sign related information from which a vital sign of the living being can be derived, a processing unit for processing the input signal and deriving vital sign related information of said living being from said input signal, an orientation estimation unit for estimating the orientation of said skin region, and a control unit for controlling an illumination unit for illuminating said skin region with light to illuminate said skin region based on the estimated orientation of said skin region and/or for controlling said processing unit to derive vital sign related information from said input signal obtained …

To allow better quality rendering of video on any display, a method is proposed of encoding, in addition to video data (VID), additional data (DD) comprising at least one change time instant (TMA_1) indicating a change in time of a characteristic luminance (CHRLUM) of the video data, which characteristic luminance summarizes the set of luminances of pixels in an image of the video data, the method comprising:....

The present invention relates to a device, system and method for obtaining a vital signal of a subject. To achieved increased robustness against motion, the device comprises a decomposition unit (12) for performing a spectral decomposition of at least two photoplethysmography detection signals being related to a physiological property of the subject and allowing extraction of a vital sign of the subject to obtain two or more spectral components of the detection signals. A weight is determined per spectral component based on an estimate of the relevance of the respective spectral component to the vital sign, derived from a characteristic of said spectral component. Finally, a vital sign is obtained by weighting at least part of the spectral components with the determined corresponding weight and extracting a vital sign from the weighted spectral components or by extracting two or more vital sign sub-signals from individual spectral components of the at least two detection signals and, weighting the extracted vital sign sub-signals with the determined weight of the corresponding spectral component, and extracting a vital sign from the weighted vital sign sub-signals.

Both Respiratory Flow (RF) and Respiratory Motion (RM) are visible in thermal recordings of infants. Monitoring these two signals usually requires landmark detection for the selection of a region of interest. Other approaches combine respiratory signals coming from both RF and RM, obtaining a Mixed Respiratory (MR) signal. The detection and classification of apneas, particularly common in preterm infants with low birth weight, would benefit from monitoring both RF and RM, or MR, signals. Therefore, we propose in this work an automatic RF pixel detector not based on facial/body landmarks. The method is based on the property of RF pixels in thermal videos, which are in areas with a smooth circular gradient. We defined 5 features combined with the use of a bank of Gabor filters that together allow selection of the RF pixels. The algorithm was tested on thermal recordings of 9 infants amounting to a total of 132 minutes acquired in a neonatal ward. On average the percentage of correctly identified RF pixels was 84%. Obstructive Apneas (OAs) were simulated as a proof of concept to prove the advantage in monitoring the RF signal compared to the MR signal. The sensitivity in the simulated OA detection improved for the RF signal reaching 73% against the 23% of the MR signal. Overall, the method yielded promising results, although the positioning and number of cameras used could be further optimized for optimal RF visibility.

OBJECTIVE: Remote pulse oximetry in visible light (VIS) is a relevant application of photoplethysmography (PPG). However, wavelengths penetrate at different depths and VIS-based pulse oximetry may not guarantee robustness to physiological variations of the skin properties. This paper shows how a simple manoeuver like a posture change can hamper the accuracy of a method relying on red and the less penetrating green wavelengths.APPROACH: Stationary subjects were measured under normoxic conditions while sitting and in the supine position. For each recording, we extracted remote PPG signals from forehead video recordings of 31 healthy adults at the red and green camera channels. The resulting normalized PPG-amplitudes, and its ratio, red-over-green (RoG), were compared between postures. The observed RoG changes were translated into estimates for arterial blood oxygen saturation (SpO 2, %) errors by means of Monte Carlo simulations of the skin tissue. Simulations were also used to compare the calibratability errors of SpO 2 in VIS against the conventional red-IR wavelengths. MAIN RESULTS: RoG differs significantly between postures (RoG: sitting, 0.100 [Formula: see text] 0.025; supine, 0.123 [Formula: see text] 0.033), mediated by PPG-amplitude changes in green. The posture interference in RoG may be mitigated by an offset correction. Without this correction, we estimated that the observed change in RoG causes SpO 2 errors >[Formula: see text]. Analogous simulations involving red-IR wavelengths indicate SpO 2 errors <[Formula: see text]. SIGNIFICANCE: Our results show that the calibrations for remote pulse oximetry in VIS require the specification of a fixed measurement position. Future work could be aimed at controlling for posture in measurements.

Low-resolution thermal cameras have already been used in the detection of respiratory flow. However, microbolometer technology has a high production cost compared to thermopile arrays. In this work, the feasibility of using a thermopile array to detect respiratory flow has been investigated in multiple settings. To prove the concept, we tested the detector on six healthy subjects. Our method automatically selects the region-of-interest by discriminating between sensor elements that output noise and flow-induced signals. The thermopile array yielded an average root mean squared error of 1.59 breaths per minute. Parameters such as distance, breathing rate, orientation, and oral or nasal breathing resulted in being fundamental in the detection of respiratory flow. The paper provides the proof-of-concept that low-cost thermopile-arrays can be used to monitor respiratory flow in a lab setting and without the need for facial landmark detection. Further development could provide a more attractive alternative for the earlier bolometer-based proposals.

Pulse-oximetry has become a core monitoring modality in most fields of medicine. Typical dual-wavelength pulse-oximeters estimate blood oxygen saturation (SpO2) levels from a relationship between the amplitudes of red and infrared photoplethysmographic (PPG) waveforms. When captured with a camera, the PPG waveforms are much weaker and consequently the measurement is more sensitive to distortions and noises. Therefore, an indirect method has recently been proposed where, instead of extracting the relative amplitudes from the individual waveforms, the waveforms are linearly combined to construct a collection of pulse signals with different pulse signatures, each corresponding to a specific oxygen saturation level. This method has been shown to outperform the conventional ratio-of-ratios based methods, especially when adding a third wavelength. Adding wavelengths, however, complicates the calibration. Inaccuracies in the calibration model threaten the performance of the method. Opto-physiological models have been shown earlier to provide useful calibration parameter estimates. In this paper, we show that the accuracy can be improved using a data-driven approach. We performed 5-fold cross validation on recordings with variations in oxygen saturation and optimized for pulse quality. All evaluated wavelength combinations, also without visible red, meet the required ISO standard accuracy with the calibration from the proposed method. This scalable approach is not only helpful to fine-tune the calibration model, but even allows computation of the calibration model parameters from scratch without prior knowledge of the data acquisition details, i.e., the properties of camera and illumination.

Apnea detection is extremely important in neonatal settings because hypoxia can lead to permanent impairment. Short cessations of breathing are very common in infants and could be used for example for the prediction of longer apneas. The aim of this study is to investigate the accuracy of our on-line cessation of breathing detector. Signals obtained through camera-based respiration monitoring were analyzed in five infants with 91 annotated cessations of breathing. The method proposed is based on the comparison of short-term and long-term standard deviations allowing the detection of sudden amplitude reduction in the signal with a low latency. A new strategy able to detect short cessations of breathing on-line was successfully validated yielding an average accuracy of 93%.