This special session is part of EMBC 2019 which takes place from July 23-27 2019 in Berlin. Registration and more information about the event can be found on the EMBC 2019 website.

Organizers:

Dr. Wenjin Wang is a scientist at Philips Research, The Netherlands. His research focuses on the camera-based vital signs monitoring and AI-assisted healthcare applications. His current and earlier doctorate work led to various journal/conference publications, patents, and potential medical products. He also has experience of chairing a workshop on a top conference.

Dr. Hubin Zhao is postdoctoral researcher at University College London, UK. He is also a member of neoLAB, Cambridge University, UK. His research interests mainly include fNIRS technology, brain-computer interfaces, and related medical applications. He has published or filed numerous journal papers, conference papers and patents, and received the Best Paper Award from IEEE BioCAS 2014.

Dr. Sander Stuijk is an assistant professor at Eindhoven University of Technology, The Netherlands. His research focusses on design trajectories for embedded signal processing application that are used in health-care monitoring and various other domains. He has been TPC member, chair and executive committee member of a large number of international conferences.


Abstract

Measuring physiological signals from the human face and body using cameras is an emerging topic that has grown rapidly in the last decade (2007-2017). Various human vital signs (e.g., heart rate (variability), respiration rate, blood oxygenation saturation, pulse transit time) can be measured remotely without skin-contact, which is convenient and comfortable for long-term or skin-sensitive health monitoring. The use of cameras also enables the analysis of human behaviors/emotions like facial expressions and high-level semantics like social interactions, which helps us to better diagnose. Optical health monitoring methods also include those that non-invasively monitor the human brain and body through the injection and measurement of red and near-infrared light. This includes pulse oximetry, which forms a critical part of patient care across the world, but is also includes a range of techniques that rely on the principles of near-infrared spectroscopy. These approaches allow the oxygenation state of muscle and brain tissues to be non-invasively monitored at the patient’s bedside. Recent advancements have even allowed human brain function to be non-invasively imaged in three dimensions, at a resolution approaching that of fMRI. This non-invasive technology will improve our understanding of a range of clinical conditions (including epilepsy, stroke, cerebral palsy and autism) and has the potential to allow real-time monitoring and detection of neuropathology at the bedside. The suitability of optical techniques for the study of vulnerable subjects also ensures that these methods are already supporting neuroscientific advancement in studies of newborn infants, children and adults in both clinical and everyday environments. With clinical AI technologies (e.g. pattern recognition), the optical sensing results, including vital signs and brain activities, can be turned into meaningful and insightful values/decisions that support medical diagnosis and human understanding, which will together lead to a broad range of healthcare applications that improve existing clinical solutions (e.g., patient monitoring and treatment) and also people’s daily lives (e.g., elderly/children care and wellness tracking).

We propose to organize an invited session at EMBC to unite the pioneering researchers from the fields of optical-based physiological and neuroimaging measurements to present the latest developments of both fields jointly. The topic of optical health monitoring would attract broad interest from conference attendees, including researchers in the fields of Biomedical Imaging, Contactless Monitoring, Neuroimaging, Image Processing and Analysis, Brain Computer Interface, Neurology, Spectroscopy, Optoelectronics, Wearable electronics, AI related healthcare applications, etc. A unique aspect of this session is that it brings together a rich set of compelling applications and novel concepts that will attract audiences from both the academic and industrial fields.


Speakers:

Prof. Steffen Leonhardt, RWTH Aachen University

Title of the presentation: Advances in using infrared thermography for vital sign monitoring

Abstract: This talk will focus on the properties and the application of infrared thermography for vital sign monitoring in neonates and adults. Specifically, we will consider heart rate and breathing rate detection next to temperature determination. We will also consider fusion with near infrared / visible light imaging.

Biographical sketch of the Speaker

Steffen Leonhardt was born in Frankfurt, Germany, in 1961. He holds a M.S. in Computer Engineering from SUNY at Buffalo, NY, USA, a Dr.-Ing. (Ph.D.) degree in Electrical Engineering from the Technical University of Darmstadt, Germany, and an M.D. in Medicine from J. W. Goethe University, Frankfurt, Germany. He has five years of R&D management experience working at Draeger Medical AG & Co. KGaA., Luebeck, Germany, and was appointed Full Professor and Head of the Philips endowed Chair of Medical Information Technology at RWTH Aachen University, Germany, in 2003. Among others, Dr. Leonhardt serves as an associate Editor of the IEEE Journal of Biomedical and Health Informatics and IEEE Transactions on Biomedical Circuits and Systems. In 2014, he became a fellow of the NRW Academy of Sciences, Humanities and the Arts in Duesseldorf. In 2015, he was appointed a distinguished lecturer by the IEEE EMBS. His research interests include physiological measurement techniques, personal health care systems and feedback control systems in medicine.

Website: https://www.medit.hia.rwth-aachen.de/en/


Dr. Wim Verkruijsse, Philips Research

Title of the presentation: Fundamental differences between conventional and remote PPG; considerations on the depth and origin of the PPG signal

Abstract: While conventional contact photo-plethysmography (PPG), best known from its implementation in pulse-oximeters, and the more recent remote PPG (rPPG) share the same basic principle, there are also fundamental differences. These differences lead to interesting questions which have been answered only partly.  We will explore these differences using a light transport model as well as experimental results. The findings have Implications for several medical applications of PPG including calibratibility of pulse-oximetry and rPPG imaging for vascular diseases.

Biographical sketch of the Speaker

As an experimental physicist Dr. Verkruijsse received his PhD in Medical Physics at the University of Amsterdam where he worked on modeling light-tissue interactions to optimize various laser dermatological applications, vascular lesions in particular. He continued this work at the Beckman Laser Institute at the University of California, Irvine, where he also explored several new diagnostic methods including pulsed photo-thermal radiometry and optical coherence tomography. At the University of Chapel Hill, North Carolina, he worked on remote sensing, atmospheric imaging in particular. Back in California, he published one of the early studies on contactless photo-plethysmograpy. Presently, he still works in this exciting field, now at Philips Research, Eindhoven, focusing on contactless pulse-oximetry.

Website: https://research.tue.nl/en/persons/wim-verkruijsse


Dr. Wenjin Wang, Philips Research

Title of the presentation: Different signature-based methods for camera-PPG measurement

Abstract: Camera-based remote photoplethysmography technology has shown great potential for contactless vital signs monitoring. Multispectral camera has been used to improve the robustness of signal extraction, by using the multi-channel combination to suppress distortions in the measured PPG-signal. In this talk, we will review different signature-based methods for PPG extraction, such as the Blood Volume Pulse Signature method (PBV, baseline work), Soft Signature based method (SoftSig, with increased signatures), Discriminative Signature based method (DisSig, with enhanced motion robustness), and Reference Signature based method (RefSig, incorporating a different sensor modality). The application of these methods and their extensions to measure other vital signs will also be introduced.

Biographical sketch of the Speaker

Wenjin Wang is a scientist at Philips Research in Eindhoven, The Netherlands and guest researcher at Eindhoven University of Technology, The Netherlands. His research is focused on camera-based vital signs monitoring and AI-related healthcare applications. His earlier PhD work (2013-2017) has improved the fundamental understanding of this technology (e.g. core algorithms) and developed various systems/applications for video health monitoring, leading to various peer-reviewed journal/conference publications and patent applications. His current work focused on improving the camera-based vital signs monitoring functions and transferring current technologies into products. Also exploring new features of camera-based physiological measurement.

Website: https://www.tue.nl/en/research/researchers/wenjin-wang


Prof. Mohamad Sawan, Polytechnique Montreal

Title of the presentation: Smart Integrated-in-Package Optode for Seizure Localisation and Subsequent Detection

Abstract: Medical devices intended for the diagnostic of neurodegenerative diseases are promising alternatives to study neural activities underlying cognitive functions and pathologies, and eventually to recover lost neural vital functions. This talk concerns a non-invasive fNIRS-based platform mainly intended for epileptic foci localization and seizures onset detection. This platform is composed of an array of optodes based on fast detectors which are intended to exploit time-domain photon-counting approach to quantify changes in the number of photons scattering back to nearly where they came from. The source and detector of an optode are placed in null/small source-detector 2-mm distance (ns-SDD) configuration. The optode integrates a 2-wavelength laser source and a time-gated single SPAD array-based detector. The achieved fast-gating circuit allows to enable a detection window sensitive to photons having propagated deep in cortical tissue. We describe the multidimensional design challenges to achieve the low-power small area system-in-package optical emitter and receiver. Application-specific microsystem architectures will be discussed, and experimental results will be demonstrated.

Biographical sketch of the Speaker

Mohamad Sawan (F’04) received the Ph.D. degree in electrical engineering from Sherbrooke University, Canada, in 1990. In 1991, he joined Polytechnique Montreal, where he is currently a Professor of microelectronics and biomedical engineering. He is leading the Microsystems Strategic Alliance of Quebec (ReSMiQ), one of the largest research centers in Canada. He is the Founder of the Polystim Neurotech Laboratory, University of Montreal, including two major research infrastructure intended to build advanced medical devices. He has authored over 700 peer-reviewed papers, two books, and 13 book chapters. He holds 15 patents. Among these patents are the urinary bladder implant, the visual stimulator for blinds, and several other medical devices. He trained more than 100 master and 40 Ph.D. students. He is a member of the Board of Governors of the IEEE CAS Society. He is a fellow of The Canadian Academy of Engineering and The Engineering Institute of Canada, and an Officer of the Quebec’s National Order. He received several awards, among them the Shanghai International Collaboration Award, the Queen Elizabeth II Golden Jubilee Medal, the Bombardier Award for technology transfer, the Jacques-Rousseau Award for achieved results in multidisciplinary research activities, the Medal of Merit from the President of Lebanon for his outstanding contributions, and the Barbara Turnbull Award for spinal cord research in Canada. He is the founder and the co-founder of several international IEEE conferences (NEWCAS, BIOCAS, ICECS, and LSC). He is the Co-Founder and the Editor-in-Chief of the IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS. He is an associate editor of the IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING and of several other international journals. He is the Founder and the Chair of the IEEE Solid State Circuits Society Montreal Chapter. In 2016, he hosted the IEEE-ISCAS, the flagship conference of the Circuits and Systems Society. He will also be the Co-Chair of EMBC 2019 and the General Chair of EMBC 2020.

Website: http://www.mohamadsawan.org/


Prof. Heidrun Wabnitz, Physikalisch-Technische Bundesanstalt

Title of the presentation: Contact and non-contact time-domain functional optical imaging of the brain

Abstract: Time-domain near-infrared spectroscopy measures the time of flight of photons travelling through the tissue. Photons arriving after short times of flight ("early photons") on average penetrate less deeply into the tissue than photons with long times of flight ("late photons"). On this basis, depth selectivity can be achieved and functional changes in the brain can be separated from changes in the extracerebral compartment. This will be illustrated with results obtained by our fibre-based time-domain optical brain imager. More recently, we worked on a non-contact scanning approach employing a fast-gated single-photon avalanche diode that allows one to measure deep absorption changes at a short source-detector separation by cutting off the huge amount of early photons and detecting late photons with high sensitivity. We could demonstrate the feasibility of imaging brain activation without contact and with 32x32 pixels at a frame rate of 1/s.

Biographical sketch of the Speaker

Prof. Heidrun Wabnitz is a senior scientist at the Department of Biomedical Optics at Physikalisch-Technische Bundesanstalt (PTB) in Berlin. She received a diploma in physics as well as a Dr. rer. nat. degree from Friedrich Schiller University in Jena. Her fields of work in Jena included picosecond spectroscopy of molecules and time-resolved fluorescence laser scanning microscopy. She joined PTB in 1991 where she focused on diffuse optical imaging and spectroscopy of tissues with picosecond time resolution, in particular in projects related to optical mammography and optical brain imaging. She is active in the development of time-domain instrumentation, modelling and data analysis, performance characterization of instruments, standardization, and clinical applications.

Website: http://spie.org/profile/Heidrun.Wabnitz-10905


Dr. Hubin Zhao, UCL/Cambridge University

Title of the presentation: Wearable, modular, high-density diffuse optical tomography systems

Abstract: Diffuse optical tomography (DOT) is an extension of near-infrared spectroscopy (NIRS) in which multiple sources and detectors of near-infrared light are arranged so as to provide 3D spatial sampling of the target object. The ability to image human brain function using a wearable device has long been a goal of NIRS and DOT research. However, existing systems are either cumbersome, have limited field of view, or provide insufficient channel density to yield 3D images. We recently presented the first ever functional images of the human brain obtained using a fibreless, high-density DOT system. In this talk, I will present an extension of this technology that furthers our goal of unrestricted functional imaging of the human brain.

Biographical sketch of the Speaker

Hubin Zhao (S’12–M’16) received the Ph.D. degree in biomedical electronics from Newcastle University, U.K., in 2016. He received the Best Paper Award from the IEEE conference on BioCAS 2014. He was the Chair of the IEEE Newcastle University Student Branch from 2014 to 2016 and is the mentor of the IEEE NCL SB. He is currently a Post-Doctoral Researcher and a Guest Lecturer with the University College London, U.K. He is also a member of neoLAB, Cambridge University, U.K. His research interests mainly include wearable fNIRS/DOT devices, brain-computer interface, biomedical circuits and neural interface, and advanced opto-electronic technology.

Website: https://neolabresearch.com/who-are-we/hubin-zhao/


DPhil. Glen Wright Colopy, University of Oxford

Title of the presentation: Clinical AI for Use in Hospitals

Abstract: Patient vital sign monitoring is essential in many medical domains, from its traditional application to critical care, to recent uses in digital therapeutics and mental health. Vital sign variability over time contains a vast amount of clinical information. However, population-based metrics and human observation can easily lose this information in the sea of inter-patient noise. This challenges the ability (of algorithms and doctors alike) to identify patients' deterioration with sufficient time to intervene. The loss of patient-specificity, in turn, hurts clinical performance via high false-alarm rates, missed early warning signs, and emergency readmissions. Intelligent computational methods are promising in their ability to both (i) handle large volumes of data and (ii) implement models sufficiently complex to examine the implications of intra-patient variability.

Building smart algorithms for real-world vital sign monitoring scenarios is a challenge that begins with the measurement device and ends with clinical interpretation of an algorithm's output. We will focus on three types of algorithms that are key to advancing the field:

  • Algorithms that secure reliable data (for analysis by subsequent algorithms)
  • Algorithms that parameterize complex machine learning models
  • Algorithms that are robust and interpretable by clinical staff

Biographical sketch of the Speaker

Glen Wright Colopy graduated with a DPhil degree from the Department of Engineering Science at Oxford in 2018. This followed his MSc in Applied Statistics at Oxford, MSc in Operations Research at North Carolina State University, and his BS degrees in Mathematics and Economics from the College of William and Mary. He work at Current Health, in Edinburgh, Scotland. His research interests include Bayesian nonparametrics for personalized medical modeling, the robust automation of statistical inference, interpretable machine learning methods, and the experimental design of machine learning-based clinical trials.

Website: http://www.robots.ox.ac.uk/~davidc/people.php