TY - JOUR AB - Detection of fetal brain signals in fetal magnetoencephalographic recordings is - due to the low signal to noise ratio - challenging for researchers in this field. Up to now, state of the art is a manual evaluation of the signal. To make the evaluation more reproducible and less time consuming, an approach using Principal Component Analysis is introduced. Locations of the channels of most importance for the first three principal components are taken into account and their possibility of resembling brain activity evaluated. Data with auditory stimulation are taken for this analysis and trigger averaged signals from the channels selected as brain activity (manually & automatically) compared. Comparisons are done with regard to their average baseline activity, activity during a window of interest and timing and amplitude of their highest auditory event-related peak. The number of evaluable data sets showed to be lower for the automated compared to manual approach but auditory event-related peaks did not differ significantly in amplitude or timing and in both cases there was a significant activity change following the tone event. The given results and the advantage of reproducibility make this method a valid alternative. AU - Moser, J. AU - Sippel, K. AU - Schleger, F. AU - Preissl, H.* C1 - 57885 C2 - 47991 SP - 6549-6552 TI - Automated detection of fetal brain signals with principal component analysis. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. PY - 2019 SN - 1557-170X ER - TY - JOUR AB - Pollen allergies are considered as a global epidemic nowadays, as they influence more than a quarter of the worldwide population, with this percentage expected to rapidly increase because of ongoing climate change. To date, alerts on high-risk allergenic pollen exposure have been provided only via forecasting models and conventional monitoring methods that are laborious. The aim of this study is to develop and evaluate our own pollen classification model based on deep neural networks. Airborne allergenic pollen have been monitored in Augsburg, Bavaria, Germany, since 2015, using a novel automatic Bio-Aerosol Analyzer (BAA 500, Hund GmbH). The automatic classification system is compared and evaluated against our own, newly developed algorithm. Our model achieves an unweighted average precision of 83.0 % and an unweighted average recall of 77.1 % across 15 classes of pollen taxa. Automatic, real-time information on concentrations of airborne allergenic pollen will significantly contribute to the implementation of timely, personalized management of allergies in the future. It is already clear that new methods and sophisticated models have to be developed so as to successfully switch to novel operational pollen monitoring techniques serving the above need. AU - Schiele, J.* AU - Rabe, F.* AU - Schmitt, M.* AU - Glaser, M.* AU - Häring, F. AU - Brunner, J.O.* AU - Bauer, B.* AU - Schuller, B.* AU - Traidl-Hoffmann, C. AU - Damialis, A. C1 - 57887 C2 - 47989 SP - 4474-4478 TI - Automated classification of airborne pollen using neural networks. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. PY - 2019 SN - 1557-170X ER - TY - JOUR AB - Fetal magnetoencephalography (fMEG) is a method to record human fetal brain signals in pregnant mothers. Nevertheless the amplitude of the fetal brain signal is very small and the fetal brain signal is overlaid by interfering signals mainly caused by maternal and fetal heart activity. Several methods are used to attenuate the interfering signals for the extraction of the fetal brain signal. However currently used methods are often affected by a reduction of the fetal brain signal or redistribution of the fetal brain signal. To overcome this limitation we developed a new fully automated procedure for removal of heart activity (FAUNA) based on Principal Component Analysis (PCA) and Ridge Regression. We compared the results with an orthogonal projection (OP) algorithm which is widely used in fetal research. The analysis was performed on simulated data sets containing spontaneous and averaged brain activity. The new analysis was able to extract fetal brain signals with an increased signal to noise ratio and without redistribution of activity across sensors compared to OP. The attenuation of interfering heart signals in fMEG data was significantly improved by FAUNA and supports fully automated evaluation of fetal brain signal. AU - Sippel, K. AU - Moser, J. AU - Schleger, F. AU - Escalona-Vargas, D.* AU - Preissl, H. AU - Rosenstiel, W.* AU - Spüler, M.* C1 - 57886 C2 - 47990 SP - 5685-5689 TI - Fully automated subtraction of heart activity for fetal magnetoencephalography data∗. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. PY - 2019 SN - 1557-170X ER - TY - JOUR AB - Breast cancer and Glioblastoma brain cancer are severe malignancies with poor prognosis. In this study, primary Glioblastoma and secondary breast cancer spheroids are formed and treated with the well-known Temozolomide and Doxorubicin chemotherapeutics, respectively. High resolution imaging of both primary and secondary cancer cell spheroids is possible using a custom multi-angle Light Sheet Fluorescence Microscope. Such a technique is successful in realizing preclinical drug screening, while enables the discrimination among physiologic tumor parameters. AU - Psycharakis, S.E.* AU - Liapis, E. AU - Zacharopoulos, A.* AU - Oraiopoulou, M.E.* AU - Papamatheakis, J.* AU - Sakkalis, V.* AU - Zacharakis, G.* C1 - 55110 C2 - 46077 SP - 866-869 TI - High resolution volumetric imaging of primary and secondary tumor spheroids using multi-angle Light Sheet Fluorescence Microscopy (LSFM). JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. VL - 2018 PY - 2018 SN - 1557-170X ER - TY - CONF AB - This study was designed to characterize in time, frequency and information domains heart period (HP) and QT interval variabilities in asymptomatic (ASYMP) long QT syndrome type 2 (LQT2) subjects. HP, approximated as the temporal distance between two consecutive R-wave peaks, and QT, approximated as the temporal distance between the R-wave peak and the T-wave offset, were automatically derived from 24h Holter recordings in 10 ASYMP LQT2 patients and 13 healthy non mutation carriers (NMC) subjects. All analyses were carried out during DAY (from 2 to 6 PM) and NIGHT (from 12 to 4 AM). Mean, variance, spectral power and complexity indices at short, medium and long time scales were assessed over HP and QT beat-to-beat series. Circadian rhythmicity was evident in both NMC and ASYMP LQT2 but ASYMP LQT2 subjects were characterized by higher HP, QT interval and HP variability during both DAY and NIGHT. In addition, multiscale complexity analysis was able to differentiate the groups by showing a higher HP complexity and a lower QT complexity at long time scales in ASYMP LQT2 during DAY. ASYMP LQT2 exhibited a different autonomic control compared to NMC and such a differentiation could be protective and assure them a lower risk profile. AU - Bari, V.* AU - Girardengo, G.* AU - Marchi, A.* AU - de Maria, B.* AU - Brink, P.A.* AU - Crotti, L. AU - Schwartz, P.J.* AU - Porta, A.* C1 - 47674 C2 - 39576 SP - 294-297 TI - Time, frequency and information domain analysis of heart period and QT variability in asymptomatic long QT syndrome type 2 patients. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. VL - 2015 PY - 2015 SN - 1557-170X ER - TY - CONF AB - A student chapter can be considered to be a miniature enterprise; however without the latter's major financial risks. Involvement in the student chapter of a professional society like IEEE at undergraduate level plays a pivotal role in the overall professional development of the student by keeping the students informed about the various career possibilities. A student chapter shapes the hitherto naive students into industry ready professionals and to suitable candidates for some of the best grad schools worldwide. This assertion has been discussed in-depth taking the example of IEEE EMBS Student Branch chapter of VIT University. It has been described how the entire process, - starting from inception of an idea to its materialization in to an activity, has shaped the volunteers and participants into better professionals. AU - Ghosh, S.* AU - Samineni, A.* AU - Mandal, S. AU - Murari, B.M.* C1 - 47672 C2 - 39577 SP - 3647-3650 TI - Enhancing professionalism among engineering students through involvements in technical societies. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. VL - 2015 PY - 2015 SN - 1557-170X ER - TY - CONF AB - In this article, we present a novel scheme for segmenting the image boundary (with the background) in optoacoustic small animal in vivo imaging systems. The method utilizes a multiscale edge detection algorithm to generate a binary edge map. A scale dependent morphological operation is employed to clean spurious edges. Thereafter, an ellipse is fitted to the edge map through constrained parametric transformations and iterative goodness of fit calculations. The method delimits the tissue edges through the curve fitting model, which has shown high levels of accuracy. Thus, this method enables segmentation of optoacoutic images with minimal human intervention, by eliminating need of scale selection for multiscale processing and seed point determination for contour mapping. AU - Mandal, S. AU - Viswanath, P.S.* AU - Yeshaswini, N.* AU - Dean-Ben, X.L. AU - Razansky, D. C1 - 47675 C2 - 39460 SP - 707-710 TI - Multiscale edge detection and parametric shape modeling for boundary delineation in optoacoustic images. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. PY - 2015 SN - 1557-170X ER - TY - JOUR AB - Fluorescence mediated tomography allows quantitative, three-dimensional imaging of optical reporter probes in whole animals and is therefore emerging as a powerful molecular imaging tool. The achievable image quality in fluorescence tomography is limited by the high-degree of light scatter in biological tissue. Time-gated detection of early-arriving and therefore minimally-scattered photons transmitted through diffusive tissue is one strategy for minimizing the effects of light scatter. In this work, we performed full-angle tomographic imaging of mice implanted with fluorescent tubes using time-gated detection of early- and later-arriving photons. This was achieved using a femtosecond laser and a high-speed, time-gated intensified CCD imager. We demonstrate that the early-transmitted fluorescent photons allow improved visualization of the fluorescence distribution, even when considering individual projections through the animal. High-fidelity image reconstruction using 72 projections in 5-degree steps using early-arriving photons is also demonstrated. AU - Niedre, M.* AU - Ntziachristos, V. C1 - 1327 C2 - 26907 CY - Minneapolis, MN SP - 6331-6334 TI - Complete angle small animal fluorescence imaging with early-arriving photons. JO - Conf. Proc. IEEE Eng. Med. Biol. Soc. PB - IEEE PY - 2009 SN - 1557-170X ER -