Highlights Fully-automated, real-time catheter and guidewire segmentation in fluoroscopy using CNNs. Two-stage training strategy based on transfer learning technique, using synthetic images with predefined labelled segmentation. Methods to reduce the need of manual pixel-level labelling to facilitate the development of CNN models for semantic segmentation, especially in the medical field. Lightweight CNN model with a decreased number of network parameters which results in more efficient training and faster run times (84% reduction in testing time compared to the state-of-the-art).

The quest for an intuitive and physiologically appropriate human machine interface for the control of dexterous prostheses is far from being completed. In the last decade, much effort has been dedicated to explore innovative control strategies based on the electrical signals generated by the muscles during contraction. In contrast, a novel approach, dubbed myokinetic interface, derives the control signals from the localization of multiple magnetic markers (MMs) directly implanted into the residual muscles of the amputee. Building on this idea, here we present an embedded system based on 32 magnetic field sensors and a real time computation platform. We demonstrate that the platform can simultaneously localize in real-time up to five MMs in an anatomically relevant workspace. The system proved highly linear (R2 = 0.99) and precise (1% repeatability), yet exhibiting short computation times (4 ms) and limited cross talk errors (10% the mean stroke of the magnets). Compared to a previous PC implementation, the system exhibited similar precision and accuracy, while being ~75% faster. These results proved for the first time the viability of using an embedded system for magnet localization. They also suggest that, by using an adequate number of sensors, it is possible to increase the number of simultaneously tracked MMs while introducing delays that are not perceivable by the human operator. This could allow to control more degrees of freedom than those controllable with current technologies.

Magnetic localizers have been widely investigated in the biomedical field, especially for intra-body applications, because they don’t require a free line-of-sight between the implanted magnets and the magnetic field sensors. However, while researchers have focused on narrow and specific aspects of the localization problem, no one has comprehensively searched for general design rules for accurately localizing multiple magnetic objectives. In this study, we sought to systematically analyse the effects of remanent magnetization, number of sensors, and geometrical configuration (i.e. distance among magnets—Linter-MM—and between magnets and sensors—LMM-sensor) on the accuracy of the localizer in order to unveil the basic principles of the localization problem. Specifically, through simulations validated with a physical system, we observed that the accuracy of the localization was mainly affected by a specific angle ($$\theta$$ θ  = tan−1(Linter-MM / LMM-sensor)), descriptive of the system geometry. In particular, while tracking nine magnets, errors below ~ 1 mm (10% of the length of the simulated trajectory) and around 9° were obtained if θ ≥  ~ 31°. The latter proved a general rule across all tested conditions, also when the number of magnets was doubled. Our results are interesting for a whole range of biomedical engineering applications exploiting multiple-magnets tracking, such as human–machine interfaces, capsule endoscopy, ventriculostomy interventions, and endovascular catheter navigation.

We recently introduced the concept of a new human-machine interface (the myokinetic control interface) to control hand prostheses. The interface tracks muscle contractions via permanent magnets implanted in the muscles and magnetic field sensors hosted in the prosthetic socket. Previously we showed the feasibility of localizing several magnets in nonrealistic workspaces. Here, aided by a 3D CAD model of the forearm, we computed the localization accuracy simulated for three different below-elbow amputation levels, following general guidelines identified in early work. To this aim we first identified the number of magnets that could fit and be tracked in a proximal (T1), middle (T2) and distal (T3) representative amputation, starting from 18, 20 and 23 eligible muscles, respectively. Then we ran a localization algorithm to estimate the poses of the magnets based on the sensor readings. A sensor selection strategy (from an initial grid of 840 sensors) was also implemented to optimize the computational cost of the localization process. Results showed that the localizer was able to accurately track up to 11 (T1), 13 (T2) and 19 (T3) magnetic markers (MMs) with an array of 154, 205 and 260 sensors, respectively. Localization errors lower than 7% the trajectory travelled by the magnets during muscle contraction were always achieved. This work not only answers the question: "how many magnets could be implanted in a forearm and successfully tracked with a the myokinetic control approach?", but also provides interesting insights for a wide range of bioengineering applications exploiting magnetic tracking.

No abstract

Restoring the function of a missing hand is still a grand challenge for bioengineers. We witnessed significant recent advances in the development of myoelectric hand prostheses and their controllers. Conversely, the wrist joint is generally overlooked in prosthetics, despite playing a fundamental role in orienting the hand in space. Indeed, it may account for several degrees of freedom of the hand in reducing compensatory movements. We acknowledge that an active, three-degree-offreedom prosthetic wrist is not a viable option for a self-contained prosthesis, therefore we merged in one design two opposed passive behaviors. The proposed wrist can automatically transition between a compliant mode, which exhibits relatively low stiffness allowing for passive motions around two rotational axes (wrist flexion/extension and radial/ulnar deviation), and a stiff mode, which grants stability during manipulation. To switch mode, no additional control input -hence cognitive burden -from the user is needed: it occurs synchronously with the prosthetic hand opening and closing motion, such that the wrist is compliant during reaching and stiff during manipulation. Our device proved reliable on the test bench and useful in a pilot test with an amputee volunteer, motivating further developments and more extensive testing to prove its effectiveness.

No abstract

No abstract