This study investigates and discusses the research findings from a rehabilitation perspective with a focus on the functional versus technical design aspects. The importance of involving potential consumers in the design of technology is highlighted. The small sample size and lack of consensus in some of the results indicates the need for further research and field testing of this new mobility device design.

Tracking of anatomical structures has multiple applications in the field of biomedical imaging, including screening, diagnosing and monitoring the evolution of pathologies. Semi-automated tracking of elongated structures has been previously formulated as a task for deep reinforcement learning (DRL), albeit it remains a challenge. We introduce a maximum entropy continuous-action DRL neural tracker capable of training from scratch in a complex environment in the presence of high noise levels, Gaussian blurring and cell detractors. The trained model is evaluated on mouse cortical two-photon microscopy images. At the expense of slightly worse robustness compared to a previously applied DRL tracker, we reach significantly higher accuracy, approaching the performance of the standard hand-engineered algorithm used for neuron tracing. The higher sample efficiency of our maximum entropy DRL tracker indicates its potential of being applied directly to small biomedical datasets in the absence of artificial models.

No abstract