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