TY - JOUR A1 - Krenzer, Adrian A1 - Banck, Michael A1 - Makowski, Kevin A1 - Hekalo, Amar A1 - Fitting, Daniel A1 - Troya, Joel A1 - Sudarevic, Boban A1 - Zoller, Wolfgang G. A1 - Hann, Alexander A1 - Puppe, Frank T1 - A real-time polyp-detection system with clinical application in colonoscopy using deep convolutional neural networks JF - Journal of Imaging N2 - Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24% on the open-source CVC-VideoClinicDB benchmark. KW - machine learning KW - deep learning KW - endoscopy KW - gastroenterology KW - automation KW - object detection KW - video object detection KW - real-time Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-304454 SN - 2313-433X VL - 9 IS - 2 ER - TY - JOUR A1 - Dorner, Daniela A1 - Mostafá, Miguel A1 - Satalecka, Konstancja T1 - High-energy alerts in the multi-messenger era JF - Universe N2 - The observation of electromagnetic counterparts to both high energy neutrinos and gravitational waves marked the beginning of a new era in astrophysics. The multi-messenger approach allows us to gain new insights into the most energetic events in the Universe such as gamma-ray bursts, supernovas, and black hole mergers. Real-time multi-messenger alerts are the key component of the observational strategies to unravel the transient signals expected from astrophysical sources. Focusing on the high-energy regime, we present a historical perspective of multi-messenger observations, the detectors and observational techniques used to study them, the status of the multi-messenger alerts and the most significant results, together with an overview of the future prospects in the field. KW - multi-messenger KW - real-time KW - high-energy KW - alerts Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-248496 SN - 2218-1997 VL - 7 IS - 11 ER - TY - JOUR A1 - Walter, Thomas A1 - Degen, Jacqueline A1 - Pfeiffer, Keram A1 - Stöckl, Anna A1 - Montenegro, Sergio A1 - Degen, Tobias T1 - A new innovative real-time tracking method for flying insects applicable under natural conditions JF - BMC Zoology N2 - Background Sixty percent of all species are insects, yet despite global efforts to monitor animal movement patterns, insects are continuously underrepresented. This striking difference between species richness and the number of species monitored is not due to a lack of interest but rather to the lack of technical solutions. Often the accuracy and speed of established tracking methods is not high enough to record behavior and react to it experimentally in real-time, which applies in particular to small flying animals. Results Our new method of real-time tracking relates to frequencies of solar radiation which are almost completely absorbed by traveling through the atmosphere. For tracking, photoluminescent tags with a peak emission (1400 nm), which lays in such a region of strong absorption through the atmosphere, were attached to the animals. The photoluminescent properties of passivated lead sulphide quantum dots were responsible for the emission of light by the tags and provide a superb signal-to noise ratio. We developed prototype markers with a weight of 12.5 mg and a diameter of 5 mm. Furthermore, we developed a short wave infrared detection system which can record and determine the position of an animal in a heterogeneous environment with a delay smaller than 10 ms. With this method we were able to track tagged bumblebees as well as hawk moths in a flight arena that was placed outside on a natural meadow. Conclusion Our new method eliminates the necessity of a constant or predictable environment for many experimental setups. Furthermore, we postulate that the developed matrix-detector mounted to a multicopter will enable tracking of small flying insects, over medium range distances (>1000m) in the near future because: a) the matrix-detector equipped with an 70 mm interchangeable lens weighs less than 380 g, b) it evaluates the position of an animal in real-time and c) it can directly control and communicate with electronic devices. KW - natural environment KW - insect tracking KW - real-time KW - movement ecology KW - heterogeneous background Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-265716 VL - 6 ER -