Navigation inside luminal organs is an arduous task that requires non-intuitive coordination between the movement of the operator's hand and the information obtained from the endoscopic video. The development of tools to automate certain tasks could alleviate the physical and mental load of doctors during interventions allowing them to focus on diagnosis and decision-making tasks. In this paper we present a synergic solution for intraluminal navigation consisting of a 3D printed endoscopic soft robot that can move safely inside luminal structures. Visual servoing based on Convolutional Neural Networks (CNNs) is used to achieve the autonomous navigation task. The CNN is trained with phantoms and in-vivo data to segment the lumen and a model-less approach is presented to control the movement in constrained environments. The proposed robot is validated in anatomical phantoms in different path configurations. We analyze the movement of the robot using different metrics such as task completion time smoothness error in the steady-state mean and maximum error. We show that our method is suitable to navigate safely in hollow environments and conditions which are different than the ones the network was originally trained on.

Transcranial Magnetic Stimulation (TMS) is a widespread technique to study corticospinal excitability. Its use in longitudinal studies is crucial to analyze the plasticity induced by rehabilitation treatments on neuromotor-impaired subjects. As TMS-related measures fluctuate with time and attention, it is crucial to collect them rapidly. Recently, it has been shown that stimulus-response (SR) curves can be acquired in less than two minutes (Mathias et al.). This technique favors the clinical use of TMS-related measures, but its intersession reliability has not been investigated yet. In this study we propose a test-retest reliability analysis of five parameters extracted from SR curves acquired on the preactivated Tibialis Anterior (TA) using the fast acquisition method. A secondary aim was to compare the reliability of these parameters for two different calculation methods of the Motor Evoked Potential (MEP) amplitude: the peak-to-peak value, referred as MEPpp, and the root mean square value, referred as MEParea. The intraclass correlation coefficients (ICC), the standard error of measurement (SEM) and the minimum detectable changes (MDC) were evaluated. Thirteen neurologically-intact elders (age 62.2±5.1) were recruited. The acquisition protocol was set up to minimize the variability of the measurement between the two sessions, carried out on separate days: an optical tracking system was used to maintain the coil placement, the EMG data were normalized over the maximum peripherally evoked action potential and a visual feedback was displayed to the testing subject to maintain the TA activation level. All the parameters, regardless the method used to compute the MEP amplitude , showed good to excellent reliability (0.75