Refine
Document Type
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Elektrode (1)
- Ganganalyse (1)
- Gehen (1)
- Hirnstimulation (1)
- Maschinelles Sehen (1)
- Pedografie (1)
- Stereokamera (1)
- computer vision (1)
- curved trajectory (1)
- deep brain stimulation (1)
Institute
Gait analysis is a systematic study of human movement. Combining wearable foot pressure sensors and machine learning (ML) solutions for a high-fidelity body pose tracking from RGB video frames could reveal more insights into gait abnormalities. However, accurate detection of heel strike (HS) and toe-off (TO) events is crucial to compute interpretable gait parameters. In this work, we present an experimental platform to study the timing of gait events using a new wearable foot pressure sensor (ActiSense System, IEE S.A., Luxembourg), and Google’s open-source ML solution MediaPipe Pose. For this purpose, two StereoPi systems were built to capture stereoscopic videos and images in real time. MediaPipe Pose was applied to the synchronized StereoPi cameras, and two algorithms (ALs) were developed to detect HS and TO events for gait and analysis. Preliminary results from a healthy subject walking on a treadmill show a mean relative deviation across all time spans of less than 4% for the ActiSense device and less than 16% for AL2 (33% for AL1) employing MediaPipe Pose on StereoPi videos. Finally, this work offers a platform for the development of sensor- and video-based ALs to automatically identify the timing of gait events in healthy individuals and those with gait disorders.
Deep brain stimulation (DBS) is a neurosurgical intervention where electrodes are permanently implanted into the brain in order to modulate pathologic neural activity. The post-operative reconstruction of the DBS electrodes is important for an efficient stimulation parameter tuning. A major limitation of existing approaches for electrode reconstruction from post-operative imaging that prevents the clinical routine use is that they are manual or semi-automatic, and thus both time-consuming and subjective. Moreover, the existing methods rely on a simplified model of a straight line electrode trajectory, rather than the more realistic curved trajectory. The main contribution of this paper is that for the first time we present a highly accurate and fully automated method for electrode reconstruction that considers curved trajectories. The robustness of our proposed method is demonstrated using a multi-center clinical dataset consisting of N = 44 electrodes. In all cases the electrode trajectories were successfully identified and reconstructed. In addition, the accuracy is demonstrated quantitatively using a high-accuracy phantom with known ground truth. In the phantom experiment, the method could detect individual electrode contacts with high accuracy and the trajectory reconstruction reached an error level below 100 μm (0.046 ± 0.025 mm). An implementation of the method is made publicly available such that it can directly be used by researchers or clinicians. This constitutes an important step towards future integration of lead reconstruction into standard clinical care.
