Prof. Dr.-Ing. Sebastian Zaunseder

Conventional medical measurement technology is often complex to use, requires contact with the body or is even invasive. Such systems/procedures are stressful for patients and medical staff and are sometimes significantly limited in their applicability.

We design, develop and validate user-friendly measurement technology, whereby hardware / sensor principles and data processing are considered together. One focus is on the use of cameras, i.e. the acquisition of various vital parameters from video recordings. However, alternatives, e.g. the use of radar or capacitive ECG as well as multimodal concepts, are also being pursued. The implementation and use of wearables also plays an important role. Applications are in clinical and non-clinical monitoring, whereby various clinical pictures (cardiovascular diseases, neurological diseases, depression), use for prevention, ambient assisted living and sport are topics.

S. Zaunseder, A. Henning, D. Wedekind, A. Trumpp, and H. Malberg, "Unobtrusive acquisition of cardiorespiratory signals," Somnologie, vol. 21, no. 2, pp. 93-100, Jun. 2017.

S. Zaunseder, A. Trumpp, D. Wedekind, and H. Malberg, "Cardiovascular assessment by imaging photoplethysmography - a review," Biomed. Eng. / Biomed. Tech, vol. 63, no. 5, pp. 617-634, Oct. 2018.

A. Woyczyk, V. Fleischhauer, and S. Zaunseder, "Adaptive Gaussian Mixture Model Driven Level Set Segmentation for Remote Pulse Rate Detection," IEEE J. Biomed. Heal. informatics, vol. 25, no. 5, pp. 1361-1372, May 2021.

Artificial intelligence (AI) methods and machine learning in particular are playing an increasingly important role in medicine. They have immense potential to utilize the increasing amount of available data for more efficient diagnostic and therapeutic procedures. Unlike in other AI applications, however, it is not just "content performance" that plays a decisive role with regard to medical use, but also factors such as interpretability, individualization and approval issues.

We deal with the use and further development of artificial intelligence methods in various contexts in order to improve medical care. One focus is on the above-mentioned aspects of interpretability, individualization and approval issues. Our own work covers feature extraction, selection and classification/clustering, whereby AI methods are used and further developed. Specific examples include the automated evaluation of sleep phases, therapy recommendation systems and the early detection or even prediction of medical emergencies. The company's own developments in the field of AI are also incorporated into its own measurement technology.

M. Scherpf, F. Gräßer, H. Malberg, and S. Zaunseder, "Predicting sepsis with a recurrent neural network using the MIMIC III database," Comput. Biol. Med, vol. 113, no. June, p. 103395, Oct. 2019.

M. Goldammer, S. Zaunseder, M. D. Brandt, H. Malberg, and F. Gräßer, "Investigation of automated sleep staging from cardiorespiratory signals regarding clinical applicability and robustness," Biomed. Signal Process. Control, vol. 71, no. August 2021, p. 103047, Jan. 2022.

F. Gräßer, F. Tesch, J. Schmitt, S. Abraham, H. Malberg, and S. Zaunseder, "A pharmaceutical therapy recommender system enabling shared decision-making," User Model. User-adapt. Interact, no. 0123456789, Aug. 2021.

Modeling and simulation can make a significant contribution to the understanding of (patho-)physiological processes and form a basis for the development of new measurement techniques (model-based development).

Various of his own works deal with modeling and combine medical background knowledge with technical solutions. His own work focuses on the interaction of light and tissue, the modeling of the cardiovascular system and the modeling of biosignals of various origins. The work serves to deepen the understanding of fundamental relationships and makes a concrete contribution to the development of innovative measurement technology and analysis methods.

J. Behar, F. Andreotti, S. Zaunseder, Q. Li, J. Oster, and G. D. Clifford, "An ECG simulator for generating maternal-foetal activity mixtures on abdominal ECG recordings," Physiol. Meas., vol. 35, no. 8, pp. 1537-1550, Jul. 2014.

V. Fleischhauer, N. Ruprecht, M. Sorelli, L. Bocchi, and S. Zaunseder, "Pulse decomposition analysis in photoplethysmography imaging," Physiol. Meas., vol. 41, no. 9, p. 095009, Oct. 2020.

• S. Zaunseder, A. Vehkaoja, V. Fleischhauer, and C. Hoog Antink, "Signal-to-noise ratio is more important than sampling rate in beat-to-beat interval estimation from optical sensors," Biomed. Signal Process. Control, vol. 74, no. January, p. Minor Revisions in Progress, 2022.

• A. Woyczyk, V. Fleischhauer, and S. Zaunseder, "Adaptive Gaussian Mixture Model Driven Level Set Segmentation for Remote Pulse Rate Detection," IEEE J. Biomed. Heal. informatics, vol. 25, no. 5, pp. 1361-1372, May 2021.
• M. Goldammer, S. Zaunseder, M. D. Brandt, H. Malberg, and F. Gräßer, "Investigation of automated sleep staging from cardiorespiratory signals regarding clinical applicability and robustness," Biomed. Signal Process. Control, vol. 71, no. August 2021, p. 103047, Jan. 2022.
• F. Gräßer, F. Tesch, J. Schmitt, S. Abraham, H. Malberg, and S. Zaunseder, "A pharmaceutical therapy recommender system enabling shared decision-making," User Model. User-adapt. Interact, no. 0123456789, Aug. 2021.

• I. Kukel, A. Trumpp, K. Plötze, A. Rost, S. Zaunseder, K. Matschke, and S. Rasche, "Contact-Free Optical Assessment of Changes in the Chest Wall Perfusion after Coronary Artery Bypass Grafting by Imaging Photoplethysmography," Appl. Sci, vol. 10, no. 18, p. 6537, Sep. 2020.
• S. Rasche, R. Huhle, E. Junghans, M. G. de Abreu, Y. Ling, A. Trumpp, and S. Zaunseder, "Association of remote imaging photoplethysmography and cutaneous perfusion in volunteers," Sci. Rep., vol. 10, no. 1, p. 16464, Dec. 2020.
• V. Fleischhauer, N. Ruprecht, M. Sorelli, L. Bocchi, and S. Zaunseder, "Pulse decomposition analysis in photoplethysmography imaging," Physiol. Meas., vol. 41, no. 9, p. 095009, Oct. 2020.
• J. A. Behar et al, "Remote health diagnosis and monitoring in the time of COVID-19," Physiol. Meas., vol. 41, no. 10, p. 10TR01, Nov. 2020.

• M. Schmidt, M. Baumert, T. Penzel, H. Malberg, and S. Zaunseder, "Nocturnal ventricular repolarization lability predicts cardiovascular mortality in the Sleep Heart Health Study," Am. J. Physiol. Circ. Physiol., vol. 316, no. 3, pp. H495-H505, Mar. 2019.
• M. Scherpf, F. Gräßer, H. Malberg, and S. Zaunseder, "Predicting sepsis with a recurrent neural network using the MIMIC III database," Comput. Biol. Med, vol. 113, no. June, p. 103395, Oct. 2019.
• S. Rasche, A. Trumpp, M. Schmidt, K. Plötze, F. Gätjen, H. Malberg, K. Matschke, M. Rudolf, F. Baum, and S. Zaunseder, "Remote Photoplethysmographic Assessment of the Peripheral Circulation in Critical Care Patients Recovering from Cardiac Surgery," Shock, vol. 52, no. 2, 2019.

• S. Zaunseder, A. Trumpp, D. Wedekind, and H. Malberg, "Cardiovascular assessment by imaging photoplethysmography - a review," Biomed. Eng. / Biomed. Tech, vol. 63, no. 5, pp. 617-634, Oct. 2018.
• D. Wedekind, D. Kleyko, E. Osipov, H. Malberg, S. Zaunseder, and U. Wiklund, "Robust Methods for Automated Selection of Cardiac Signals After Blind Source Separation," IEEE Trans. Biomed. Eng, vol. 65, no. 10, pp. 2248-2258, Oct. 2018.
• A. Trumpp, J. Lohr, D. Wedekind, M. Schmidt, M. Burghardt, A. R. Heller, H. Malberg, and S. Zaunseder, "Camera-based photoplethysmography in an intraoperative setting," Biomed. Eng. Online, vol. 17, no. 1, p. 33, Mar. 2018.
• M. Schmidt, M. Baumert, H. Malberg, and S. Zaunseder, "Iterative two-dimensional signal warping-Towards a generalized approach for adaption of one-dimensional signals," Biomed. Signal Process. Control, vol. 43, pp. 311-319, May 2018.

• Cardiovascular system
• Medical technology systems
• Applied Biosignal Processing - beat detection
• Applied Biosignal Processing - introduction to machine learning
• Practical course 1
• Practical course 2
• Presentation technology
• Seminar Biomedical Engineering

• Applied biomedical engineering
• Machine Learning