@article{RotheBergerWelkeretal.2023, author = {Rothe, Felix and Berger, J{\"o}rn and Welker, Pia and Fiebelkorn, Richard and Kupper, Stefan and Kiesel, Denise and Gedat, Egbert and Ohrndorf, Sarah}, title = {Fluorescence optical imaging feature selection with machine learning for differential diagnosis of selected rheumatic diseases}, series = {Frontiers in Medicine}, volume = {10}, journal = {Frontiers in Medicine}, publisher = {Frontiers}, issn = {2296-858X}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-17922}, year = {2023}, abstract = {Background and objective: Accurate and fast diagnosis of rheumatic diseases affecting the hands is essential for further treatment decisions. Fluorescence optical imaging (FOI) visualizes inflammation-induced impaired microcirculation by increasing signal intensity, resulting in different image features. This analysis aimed to find specific image features in FOI that might be important for accurately diagnosing different rheumatic diseases. Patients and methods: FOI images of the hands of patients with different types of rheumatic diseases, such as rheumatoid arthritis (RA), osteoarthritis (OA), and connective tissue diseases (CTD), were assessed in a reading of 20 different image features in three phases of the contrast agent dynamics, yielding 60 different features for each patient. The readings were analyzed for mutual differential diagnosis of the three diseases (One-vs-One) and each disease in all data (One-vs-Rest). In the first step, statistical tools and machine-learning-based methods were applied to reveal the importance rankings of the features, that is, to find features that contribute most to the model-based classification. In the second step machine learning with a stepwise increasing number of features was applied, sequentially adding at each step the most crucial remaining feature to extract a minimized subset that yields the highest diagnostic accuracy. Results: In total, n = 605 FOI of both hands were analyzed (n = 235 with RA, n = 229 with OA, and n = 141 with CTD). All classification problems showed maximum accuracy with a reduced set of image features. For RA-vs.-OA, five features were needed for high accuracy. For RA-vs.-CTD ten, OA-vs.-CTD sixteen, RA-vs.-Rest five, OA-vs.-Rest eleven, and CTD-vs-Rest fifteen, features were needed, respectively. For all problems, the final importance ranking of the features with respect to the contrast agent dynamics was determined. Conclusions: With the presented investigations, the set of features in FOI examinations relevant to the differential diagnosis of the selected rheumatic diseases could be remarkably reduced, providing helpful information for the physician.}, language = {en} } @inproceedings{PulwerFiebelkornZeschetal.2019, author = {Pulwer, Silvio and Fiebelkorn, Richard and Zesch, Christoph and Steglich, Patrick and Villringer, Claus and Villasmunta, Francesco and Gedat, Egbert and Handrich, Jan and Schrader, Sigurd and Vandenhouten, Ralf}, title = {Endoscopic orientation by multimodal data fusion}, series = {Proc. SPIE 10931, MOEMS and Miniaturized Systems XVIII}, booktitle = {Proc. SPIE 10931, MOEMS and Miniaturized Systems XVIII}, issn = {1996-756X}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-11420}, year = {2019}, abstract = {To improve the feasibility of endoscopic inspection processes we developed a system that provides online information about position, orientation and viewing direction of endoscopes, to support the analysis of endoscopic images and to ease the operational handling of the equipment. The setup is based on an industrial endoscope consisting of a camera, various MEMS and multimodal data fusion. The software contains algorithms for feature and geometric structure recognition as well as Kalman filters. To track the distal end of the endoscope and to generate 3D point cloud data in real time the optical and photometrical characteristics of the system are registered and the movement of the endoscope is reconstructed by using image processing techniques.}, language = {en} } @misc{GedatFechnerFiebelkornetal.2018, author = {Gedat, Egbert and Fechner, Pascal and Fiebelkorn, Richard and Vandenhouten, Jan and Vandenhouten, Ralf}, title = {Image recognition of multi-perspective data for intelligent analysis of gestures and actions}, series = {Wissenschaftliche Beitr{\"a}ge 2018}, volume = {22}, journal = {Wissenschaftliche Beitr{\"a}ge 2018}, issn = {0949-8214}, doi = {10.15771/0949-8214_2018_3}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-10230}, pages = {25 -- 30}, year = {2018}, abstract = {The BERMUDA project started in January 2015 and was successfully completed after less than three years in August 2017. A technical set-up and an image processing and analysis software were developed to record and evaluate multi-perspective videos. Based on two cameras, positioned relatively far from one another with tilted axes, synchronized videos were recorded in the laboratory and in real life. The evaluation comprised the background elimination, the body part classification, the clustering, the assignment to persons and eventually the reconstruction of the skeletons. Based on the skeletons, machine learning techniques were developed to recognize the poses of the persons and next for the actions performed. It was, for example, possible to detect the action of a punch, which is relevant in security issues, with a precision of 51.3 \% and a recall of 60.6 \%.}, language = {en} } @misc{GedatFechnerFiebelkornetal.2017, author = {Gedat, Egbert and Fechner, Pascal and Fiebelkorn, Richard and Vandenhouten, Ralf}, title = {Szenenanalyse und Unterscheidung der Skelette mehrerer Menschen in digitalen Bildern mit Graphentheorie durch eine k-k{\"u}rzeste-disjunkte-Wege-Suche}, series = {Wissenschaftliche Beitr{\"a}ge 2017}, volume = {21}, journal = {Wissenschaftliche Beitr{\"a}ge 2017}, issn = {0949-8214}, doi = {10.15771/0949-8214_2017_4}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:526-opus4-9394}, pages = {31 -- 35}, year = {2017}, abstract = {Das Erkennen von Personen auf Fotos und in Videos geschieht in aktuellen Klassifizierungsverfahren durch die Zuordnung eines K{\"o}perteils zu jedem Pixel. Anschließend werden die gefundenen K{\"o}rperteile zu Skeletten zusammengefasst. Im Falle mehrerer abgebildeter Personen ergibt sich das Problem der Zuordnung der K{\"o}rperteile zu den verschiedenen Skeletten. Es wurde in dieser Arbeit ein auf dem Suurballe-Algorithmus basierendes graphentheoretisches Verfahren entwickelt, das diese Aufgabe l{\"o}st. Aufbauend auf im Wesentlichen abstandsabh{\"a}ngigen Kantengewichten wird eine k-k{\"u}rzeste-disjunkte-Wege-Suche durchgef{\"u}hrt. Unter Einbezug von m{\"o}glicherweise fehlenden K{\"o}rperteilen durch Unsichtbar-Knoten und automatisches Aussortieren zu viel gefundener K{\"o}rperteile werden so die k-optimalen Skelette gefunden. Die Methode wurde an idealisierten computergenerierten Bildern mit einer Trefferquote von 100 \% gefundener Personen getestet. Ein Test mit realen Bilddaten lieferte eine Trefferquote von 71,7 \%.}, language = {de} }