Lebenswissenschaften und Ethik
Refine
Year of publication
Document Type
- conference proceeding (article) (385) (remove)
Is part of the Bibliography
- no (385)
Keywords
- Deep Learning (6)
- Gehirn (5)
- Schnittdarstellung (5)
- Simulation (5)
- Bildsegmentierung (4)
- Registrierung <Bildverarbeitung> (4)
- Automatische Klassifikation (3)
- Bildgebendes Verfahren (3)
- Bildverarbeitung (3)
- Biomechanik (3)
Institute
- Fakultät Angewandte Sozial- und Gesundheitswissenschaften (185)
- Institut für Sozialforschung und Technikfolgenabschätzung (IST) (137)
- Labor Empirische Sozialforschung (136)
- Regensburg Center of Biomedical Engineering - RCBE (88)
- Fakultät Maschinenbau (86)
- Labor Biomechanik (LBM) (68)
- Fakultät Informatik und Mathematik (66)
- Regensburg Medical Image Computing (ReMIC) (43)
- Fakultät Elektro- und Informationstechnik (41)
- Labor für Technikfolgenabschätzung und Angewandte Ethik (LaTe) (29)
Begutachtungsstatus
- peer-reviewed (58)
- begutachtet (2)
Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.
Training data for Neural Networks is often scarce in the medical domain, which often results in models that struggle to generalize and consequently showpoor performance on unseen datasets. Generally, adding augmentation methods to the training pipeline considerably enhances a model’s performance. Using the dataset of the Foot Ulcer Segmentation Challenge, we analyze two additional augmentation methods in the domain of chronic foot wounds - local warping of wound edges along with projection and blurring of shapes inside wounds. Our experiments show that improvements in the Dice similarity coefficient and Normalized Surface Distance metrics depend on a sensible selection of those augmentation methods.
Preliminary considerations on the form-finding of a tensegrity joint to be used in dynamic orthoses
(2024)
The utilization of virtual reality (VR) technology has shown promise in various therapeutic applications, particularly in exposure therapy
for reducing fear of certain situations objects or activities, e.g. fear of height, or negative evaluation of others in social situations. VR has been shown to yield positive outcomes in follow-up studies, and provides a safe and ecological therapeutic environment for therapists and their patients. This paper presents a collaborative
effort to develop a VR speech therapy system which simulates a virtual audience for users to practice their public speaking skills. We describe a novel web-based graphica user interface that enables
therapists to manage the therapy session using a simple timeline. Lastly, we present the results from a qualitative study with therapists and teachers with functional dysphonia, which highlight the potential of such an application to support and augment the therapists’ work and the remaining challenges regarding the design of natural interactions, agent behaviours and scenario customisation for patients.
This paper is based on the talk of the same title delivered at the “Dock of Learning” Symposium. I reflect on design research with an eye on the critical issues of our time. Design research has the potential to take on these issues; however, there are challenges. A threatening one, I see, is the divergence of design research and art research. I attempt to tackle this by examining Jonas’ Research through Design and Borgdorff’s Artistic Research with help from John Dewey’s philosophy.
Theoretical considerations on a 2D compliant tensegrity joint in context of a biomedical application
(2023)
In this paper, a two-dimensional compliant tensegrity joint was investigated for potential biomedical applications such as orthotics or exoskeletons. The structure consists of two compressed members connected by five compliant tensioned members. The concept is based on the tensegrity principle, which allows the realization of dynamic orthoses without conventional hinge joints. Another advantage is the adaptability to the individual needs of the patient through a suitable design of the structure and the careful selection of the characteristics of the elements. Using geometric nonlinear analysis, the mechanical behavior of the structure was investigated, focusing on mechanical compliance. The main objective was to determine the influence of the initial length and stiffness of the tensioned members and the influence of the magnitude of external forces on the overall stiffness of the movable member of the structure. The results highlight the significant impact of member parameters on the structure's stiffness and movability under varying load magnitudes. The research laid the foundation for future development of dynamic orthoses based on this structure.
In diesem Beitrag erfolgt die theoretische Untersuchung einer zweidimensionalen nachgiebigen Tensegrity-Struktur in Hinsicht auf ihre potenzielle Eignung als Basisstruktur für eine dynamische Handorthese. Translatorische und rotatorische relative Bewegungsmöglichkeiten zwischen den Drucksegmenten der Struktur sind möglich, da diese Segmente durch nachgiebige Zugsegmente miteinander verbunden sind. Die Form der Struktur und ihre Vorspannung in einer statisch stabilen Gleichgewichtskonfiguration werden mit Hilfe der Minimierung des Kräfte- und Momentenungleichgewichts, der Betrachtung der potentiellen Energie der Struktur und einem Ansatz mittels statischer Finite-Elemente-Methode (FEM) in Abhängigkeit der Segmentparameter untersucht.
Der Beitrag zeigt, dass es sich bei der populären Figur eines ‚richtigen‘ oder gesunden Körpergewichts um eine diskursive soziale Konstruktion handelt, die aus der Veralltäglichung eines genuin naturwissenschaftlichen Diskurses im 19. und 20. Jahrhundert hervorging. Das 21. Jahrhundert steht für die Etablierung eines Wissensregimes und gleichzeitig für neue Spielräume gesellschaftlichen Wissens, die sich in einer sogenannten „Bildergesellschaft“ unter anderem in den sozialen Medien konstituieren. Eine wissenssoziologische Diskursanalyse medizinischer und wissenschaftlicher Fachliteratur, gesundheitspolitischer Kampagnen, einschlägiger Internetforen, -seiten und Blogs von Body Positive-Aktivist*innen entschlüsselt dynamische Bewegungen und Gegen-Bewegungen im Umfeld des ‚richtigen‘ Körpergewichts. Die bisherige hierarchische Ordnung von Wissen weist zwei Diskursstränge auf: Eine negative Bewertung und Moralisierung von Übergewicht sowie die Konjunktur eines Body Shaping. Gegen die kollektive Selbstoptimierung in Richtung eines fitten, schlanken Körpers formiert sich allerdings seit einiger Zeit Widerstand. Dieser organisiert sich zum einen in wissenschaftlicher Hinsicht, zum anderen wird ein neues Schönheits- und Körperverständnis populär. Die Initiativen der Fat Studies und der Body Positivity-Bewegung erreichen bereits weltweit diskursive Sichtbarkeit und könnten normatives Wissen langfristig entmachten.