Multi-Task Convolutional Neural Network for Patient Detection and Skin Segmentation in Continuous Non-Contact Vital Sign Monitoring

Patient detection and skin segmentation are important steps in non-contact vital sign monitoring as skin regions contain pulsatile information required for the estimation of vital signs such as heart rate, respiratory rate and peripheral oxygen saturation (SpO2). Previous methods based on face detection or colour-based image segmentation are less reliable in a hospital setting. In this paper, we develop a multi-task convolutional neural network (CNN) for detecting the presence of a patient and segmenting the patient’s skin regions. The multi-task model has a shared core network with two branches: a segmentation branch which was implemented using a fully convolutional network, and a classification branch which was implemented using global average pooling. The whole network was trained using images from a clinical study conducted in the neonatal intensive care unit (NICU) of the John Radcliffe hospital, Oxford, UK. Our model can produce accurate results and is robust to changes in different skin tones, pose variations, lighting variations, and routine interaction of clinical staff.

[1]  Daniel McDuff,et al.  Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam , 2011, IEEE Transactions on Biomedical Engineering.

[2]  L. Tarassenko,et al.  Continuous non-contact vital sign monitoring in neonatal intensive care unit , 2014, Healthcare technology letters.

[3]  F. Mastik,et al.  Contactless Multiple Wavelength Photoplethysmographic Imaging: A First Step Toward “SpO2 Camera” Technology , 2005, Annals of Biomedical Engineering.

[4]  B. Li,et al.  Non-contact detection of oxygen saturation based on visible light imaging device using ambient light. , 2013, Optics express.

[5]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[6]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[7]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[8]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[9]  Rosalind W. Picard,et al.  Non-contact, automated cardiac pulse measurements using video imaging and blind source separation , 2022 .

[10]  L. O. Svaasand,et al.  Remote plethysmographic imaging using ambient light. , 2008, Optics express.

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  L. Tarassenko,et al.  Non-contact video-based vital sign monitoring using ambient light and auto-regressive models , 2014, Physiological measurement.

[13]  Nikolaos G. Bourbakis,et al.  A survey of skin-color modeling and detection methods , 2007, Pattern Recognit..

[14]  James M. Rehg,et al.  Statistical Color Models with Application to Skin Detection , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[15]  Kual-Zheng Lee,et al.  Contact-Free Heart Rate Measurement Using a Camera , 2012, 2012 Ninth Conference on Computer and Robot Vision.

[16]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[17]  W. Verkruysse,et al.  Non-contact heart rate monitoring utilizing camera photoplethysmography in the neonatal intensive care unit - a pilot study. , 2013, Early human development.

[18]  Frédo Durand,et al.  Eulerian video magnification for revealing subtle changes in the world , 2012, ACM Trans. Graph..

[19]  Ashok Veeraraghavan,et al.  DistancePPG: Robust non-contact vital signs monitoring using a camera , 2015, Biomedical optics express.

[20]  Andrew Blake,et al.  Geodesic star convexity for interactive image segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Frédéric Bousefsaf,et al.  Continuous wavelet filtering on webcam photoplethysmographic signals to remotely assess the instantaneous heart rate , 2013, Biomed. Signal Process. Control..

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Don P. Mitchell,et al.  Spectrally optimal sampling for distribution ray tracing , 1991, SIGGRAPH.