Introduction: Osteoarthritis (OA) mainly affects weight-bearing joints such as the knee. The exact pathomechanics of OA remain a major focus of research, with the aim to slow down progression or prevent the development of OA altogether. By accurately characterizing knee kinematics during functional activities, mechanical factors contributing to the progression and onset of knee OA can be identified. Knee kinematics are obtained by registering a three-dimensional (3D) bone model derived from magnetic resonance imaging (MRI) to two dimensional (2D) fluoroscopic images, a process that relies on accurate bone segmentation. Automated segmentation is a promising way to reduce the workload of manual segmentation. This thesis evaluated what impact the variability in automated segmentation of the femur and tibia on monoplane fluoroscopy has on 3D-2D registration accuracy and knee kinematics.

Methods: A dataset consisting of a double-echo steady-state MRI sequence and 78 fluoroscopy images of one healthy subject. A nnU-net was trained to automatically segment the fluoroscopic images. One automated segmentation was selected as reference and visually checked for correctness. 14 typically occurring segmentation errors were identified based on visual inspection of the automated segmentations and applied as variant segmentations. 3D-2D registration was performed with the reference and variant segmentations. A descriptive analysis was carried out to compare reference and variant segmentations.

Results: Overall, typically occurring segmentation errors in automatic registration resulted in a submillimeter and subdegree error in registration and subdegree error in knee kinematics rotations compared to the reference segmentations. Larger errors existed for dilated, eroded, out-of-frame and altered tibial joint contour variants, especially for the out-of-plane direction (5.64 mm) and two rotational axes (2.71°). Kinematic translations showed larger errors across all variants with errors up to 11.10 mm in anterior/posterior direction.

Conclusion: Small, typical inaccuracies in automated femur and tibia segmentations in monoplane fluoroscopy do not have a substantial impact on the registration accuracy and knee kinematics. However, errors that omit (out-of-frame) or misrepresent (tibial joint contour) distinct bone contours can cause larger errors. In addition, caution should be exercised with the exact delineation, i.e. erosion or dilation, of bone contours. Future research should focus on evaluating the generalizability of the findings from this thesis and improving the registration accuracy in general.
... Read more

As artificial intelligence agents become widespread, markets may shift towards virtual agent economies, in which agents transact with one another at speeds beyond human oversight and without knowing each other's intentions. Agents in such economies must decide whom to trust, yet a single trust score cannot tell whether a partner failed because it was unable or because it was unwilling. The socio-cognitive model of trust draws this distinction by decomposing trust into competence, willingness and opportunity, but it specifies no procedure for computing these beliefs. We address this gap with TrustForge, a language model agent architecture that operationalizes the socio-cognitive trust model, evaluated in the TruthMarketTwin environment. TrustForge uses a two-stage reasoning pipeline to ground each dimension in environmental observations and compose them into an overall trust score that guides delegation, while preserving the distinction between capability and intent. Across two market types and two seller budgets, trust protects buyers from seller deception and improves their utility per purchase, reducing deceptive sell-through from 28.10% to 13.82% in the reputation-only market. Buyers compose trust non-compensatorily, and a single deceptive sale decreases trust by more than an honest sale increases it, consistent with the asymmetry principle of human trust. We further extend trust to testimony, so that agents also assess each other's reports against their own observations. Toward their peers, buyers attribute high willingness but lower competence, separating capability from intent. However, buyers do not make this separation for sellers, lowering all three dimensions together after a deceptive sale. The code can be found at: https://github.com/tapri-lab/trustforge. ... Read more

Advanced materials promise to cut material use and enable structural designs that conventional materials cannot achieve. Composite materials — materials that combine two or more constituents — such as fiber-reinforced polymers, are an example of an advanced material whose properties can exceed those of traditional building materials. However, developing a new material for a specific structure is a costly process that requires vast experimental trial and error. Virtual testing using computational models has the potential to reduce this cost and accelerate material innovation. Computational methods have been developed for these advanced materials that account for phenomena at a very small scale (the microscale) while simulating a large structure (the macroscale). The high fidelity of these multiscale methods imposes a significant computational burden. Running one such multiscale simulation could scale up to take years, and designing and optimizating a structure often requires simulating many variations. To enable virtual testing and optimization of these materials, we thus require acceleration techniques. A popular avenue to accelerate these simulations is using machine learning.

Data-driven machine learning techniques allow for approximating the simulation outcome at a fraction of the computational cost. The microscale material behaviour can be replaced by a data-driven surrogate model that is then integrated in the macroscale simulation. These data-driven surrogate models can make accurate predictions by learning from precomputed microscale simulations. While promising, this approach faces several challenges: rich microscale information is lost, predictions become unreliable, and training an accurate surrogate model requires large quantities of training data. This dissertation develops methods aimed at addressing each of these challenges.

To enable optimization, a model should predict well for a range of different microstructures. However, most surrogates avoid the microscale completely, and directly predict homogenized quantities for one specific microstructure. We develop a surrogate that instead predicts the rich microscale response for varying microstructures, using a graph neural network that maps onto any microscale mesh. Regardless of the surrogate used, when little data is available, it can become unreliable and lead to inaccurate simulations. We therefore introduce a method that adaptively switches between a fast surrogate and the slow ground-truth model, using the surrogate only in the range on which it has been trained. The uncertainty of a probabilistic surrogate informs the switch, and a phase-field at the macroscale smoothens the transition to increase stability. This approach increases the reliability of data-driven multiscale simulations, leading to accurate simulations even for inadequately trained surrogates. Finally, we enrich an existing surrogate, a physically recurrent neural network, with microstructural descriptors. The strong inductive bias in this model enables it to learn with very few training samples. With this model, we demonstrate that data-driven multiscale simulations can capture high-fidelity microscopic effects and are sufficiently tractable to enable multiscale optimization.
... Read more

Lorentz and reluctance actuators are widely applied in high-precision motion systems as they provide non-contact forces without backlash, thereby enabling nanometer-scale positioning. However, sustaining gravitational offset forces requires a continuous current supply, causing heat losses and consequently thermal positioning drift. Hybrid tunable magnet actuators (HTMAs) provide adjustable offset forces without continuous power consumption. However, existing designs are single-DoF, short-stroke (0.5 - 1 mm), and require flexures to compensate for parasitic forces. This work presents an HTMA for gravity compensation in a 6-DoF levitated stage with an increased 4 mm XYZ-stroke and continuous Z-rotation. A force tuning range of -7.39 N to 7.41 N is experimentally demonstrated at the central mover position. In addition, the actuator exhibits relatively low stiffness variation and limited parasitic forces and torques over the motion range. For efficient tunable gravity compensation, the HTMA could operate in parallel with a passive magnetic system that provides the nominal force and counteracts the HTMA stiffness ... Read more