A Fast and Robust Deep Convolutional Neural Networks for Complex Human Activity Recognition Using Smartphone.

As a significant role in healthcare and sports applications, human activity recognition (HAR) techniques are capable of monitoring humans' daily behavior. It has spurred the demand for intelligent sensors and has been giving rise to the explosive growth of wearable and mobile devices. They provide the most availability of human activity data (big data). Powerful algorithms are required to analyze these heterogeneous and high-dimension streaming data efficiently. This paper proposes a novel fast and robust deep convolutional neural network structure (FR-DCNN) for human activity recognition (HAR) using a smartphone. It enhances the effectiveness and extends the information of the collected raw data from the inertial measurement unit (IMU) sensors by integrating a series of signal processing algorithms and a signal selection module. It enables a fast computational method for building the DCNN classifier by adding a data compression module. Experimental results on the sampled 12 complex activities dataset show that the proposed FR-DCNN model is the best method for fast computation and high accuracy recognition. The FR-DCNN model only needs 0.0029 s to predict activity in an online way with 95.27% accuracy. Meanwhile, it only takes 88 s (average) to establish the DCNN classifier on the compressed dataset with less precision loss 94.18%.

Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network.

In robot control with physical interaction, like robot-assisted surgery and bilateral teleoperation, the availability of reliable interaction force information has proved to be capable of increasing the control precision and of dealing with the surrounding complex environments. Usually, force sensors are mounted between the end effector of the robot manipulator and the tool for measuring the interaction forces on the tooltip. In this case, the force acquired from the force sensor includes not only the interaction force but also the gravity force of the tool. Hence the tool dynamic identification is required for accurate dynamic simulation and model-based control. Although model-based techniques have already been widely used in traditional robotic arms control, their accuracy is limited due to the lack of specific dynamic models. This work proposes a model-free technique for dynamic identification using multi-layer neural networks (MNN). It utilizes two types of MNN architectures based on both feed-forward networks (FF-MNN) and cascade-forward networks (CF-MNN) to model the tool dynamics. Compared with the model-based technique, i.e., curve fitting (CF), the accuracy of the tool identification is improved. After the identification and calibration, a further demonstration of bilateral teleoperation is presented using a serial robot (LWR4+, KUKA, Germany) and a haptic manipulator (SIGMA 7, Force Dimension, Switzerland). Results demonstrate the promising performance of the model-free tool identification technique using MNN, improving the results provided by model-based methods.

Development of a bench-top device for parallel climate-controlled recordings of neuronal cultures activity with microelectrode arrays.

Two binding requirements for in vitro studies on long-term neuronal networks dynamics are (i) finely controlled environmental conditions to keep neuronal cultures viable and provide reliable data for more than a few hours and (ii) parallel operation on multiple neuronal cultures to shorten experimental time scales and enhance data reproducibility. In order to fulfill these needs with a Microelectrode Arrays (MEA)-based system, we designed a stand-alone device that permits to uninterruptedly monitor neuronal cultures activity over long periods, overcoming drawbacks of existing MEA platforms. We integrated in a single device: (i) a closed chamber housing four MEAs equipped with access for chemical manipulations, (ii) environmental control systems and embedded sensors to reproduce and remotely monitor the standard in vitro culture environment on the lab bench (i.e. in terms of temperature, air CO2 and relative humidity), and (iii) a modular MEA interface analog front-end for reliable and parallel recordings. The system has been proven to assure environmental conditions stable, physiological and homogeneos across different cultures. Prolonged recordings (up to 10 days) of spontaneous and pharmacologically stimulated neuronal culture activity have not shown signs of rundown thanks to the environmental stability and have not required to withdraw the cells from the chamber for culture medium manipulations. This system represents an effective MEA-based solution to elucidate neuronal network phenomena with slow dynamics, such as long-term plasticity, effects of chronic pharmacological stimulations or late-onset pathological mechanisms.

The Neural Correlates of Long-Term Carryover following Functional Electrical Stimulation for Stroke.

Neurorehabilitation effective delivery for stroke is likely to be improved by establishing a mechanistic understanding of how to enhance adaptive plasticity. Functional electrical stimulation is effective at reducing poststroke foot drop; in some patients, the effect persists after therapy has finished with an unknown mechanism. We used fMRI to examine neural correlates of functional electrical stimulation key elements, volitional intent to move and concurrent stimulation, in a group of chronic stroke patients receiving functional electrical stimulation for foot-drop correction. Patients exhibited task-related activation in a complex network, sharing bilateral sensorimotor and supplementary motor activation with age-matched controls. We observed consistent separation of patients with and without carryover effect on the basis of brain responses. Patients who experienced the carryover effect had responses in supplementary motor area that correspond to healthy controls; the interaction between experimental factors in contralateral angular gyrus was seen only in those without carryover. We suggest that the functional electrical stimulation carryover mechanism of action is based on movement prediction and sense of agency/body ownership-the ability of a patient to plan the movement and to perceive the stimulation as a part of his/her own control loop is important for carryover effect to take place.

Down-sizing of neuronal network activity and density of presynaptic terminals by pathological acidosis are efficiently prevented by Diminazene Aceturate.

Local acidosis is associated with neuro-inflammation and can have significant effects in several neurological disorders, including multiple sclerosis, brain ischemia, spinal cord injury and epilepsy. Despite local acidosis has been implicated in numerous pathological functions, very little is known about the modulatory effects of pathological acidosis on the activity of neuronal networks and on synaptic structural properties. Using non-invasive MRI spectroscopy we revealed protracted extracellular acidosis in the CNS of Experimental Autoimmune Encephalomyelitis (EAE) affected mice. By multi-unit recording in cortical neurons, we established that acidosis affects network activity, down-sizing firing and bursting behaviors as well as amplitudes. Furthermore, a protracted acidosis reduced the number of presynaptic terminals, while it did not affect the postsynaptic compartment. Application of the diarylamidine Diminazene Aceturate (DA) during acidosis significantly reverted both the loss of neuronal firing and bursting and the reduction of presynaptic terminals. Finally, in vivo DA delivery ameliorated the clinical disease course of EAE mice, reducing demyelination and axonal damage. DA is known to block acid-sensing ion channels (ASICs), which are proton-gated, voltage-insensitive, Na(+) permeable channels principally expressed by peripheral and central nervous system neurons. Our data suggest that ASICs activation during acidosis modulates network electrical activity and exacerbates neuro-degeneration in EAE mice. Therefore pharmacological modulation of ASICs in neuroinflammatory diseases could represent a new promising strategy for future therapies aimed at neuro-protection.

Re-thinking the role of motor cortex: context-sensitive motor outputs?

The standard account of motor control considers descending outputs from primary motor cortex (M1) as motor commands and efference copy. This account has been challenged recently by an alternative formulation in terms of active inference: M1 is considered as part of a sensorimotor hierarchy providing top-down proprioceptive predictions. The key difference between these accounts is that predictions are sensitive to the current proprioceptive context, whereas efference copy is not. Using functional electric stimulation to experimentally manipulate proprioception during voluntary movement in healthy human subjects, we assessed the evidence for context sensitive output from M1. Dynamic causal modeling of functional magnetic resonance imaging responses showed that FES altered proprioception increased the influence of M1 on primary somatosensory cortex (S1). These results disambiguate competing accounts of motor control, provide some insight into the synaptic mechanisms of sensory attenuation and may speak to potential mechanisms of action of FES in promoting motor learning in neurorehabilitation.

Spatio-temporal layers based intra-operative stereo depth estimation network via hierarchical prediction and progressive training.

BACKGROUND AND OBJECTIVE: Safety of robotic surgery can be enhanced through augmented vision or artificial constraints to the robotl motion, and intra-operative depth estimation is the cornerstone of these applications because it provides precise position information of surgical scenes in 3D space. High-quality depth estimation of endoscopic scenes has been a valuable issue, and the development of deep learning provides more possibility and potential to address this issue. METHODS: In this paper, a deep learning-based approach is proposed to recover 3D information of intra-operative scenes. To this aim, a fully 3D encoder-decoder network integrating spatio-temporal layers is designed, and it adopts hierarchical prediction and progressive learning to enhance prediction accuracy and shorten training time. RESULTS: Our network gets the depth estimation accuracy of MAE 2.55±1.51 (mm) and RMSE 5.23±1.40 (mm) using 8 surgical videos with a resolution of 1280×1024, which performs better compared with six other state-of-the-art methods that were trained on the same data. CONCLUSIONS: Our network can implement a promising depth estimation performance in intra-operative scenes using stereo images, allowing the integration in robot-assisted surgery to enhance safety.

Towards safer robot-assisted surgery: A markerless augmented reality framework.

Robot-assisted surgery is rapidly developing in the medical field, and the integration of augmented reality shows the potential to improve the operation performance of surgeons by providing more visual information. In this paper, we proposed a markerless augmented reality framework to enhance safety by avoiding intra-operative bleeding, which is a high risk caused by collision between surgical instruments and delicate blood vessels (arteries or veins). Advanced stereo reconstruction and segmentation networks are compared to find the best combination to reconstruct the intra-operative blood vessel in 3D space for registration with the pre-operative model, and the minimum distance detection between the instruments and the blood vessel is implemented. A robot-assisted lymphadenectomy is emulated on the da Vinci Research Kit in a dry lab, and ten human subjects perform this operation to explore the usability of the proposed framework. The result shows that the augmented reality framework can help the users to avoid the dangerous collision between the instruments and the delicate blood vessel while not introducing an extra load. It provides a flexible framework that integrates augmented reality into the medical robotic platform to enhance safety during surgery.

MUNDUS project: MUltimodal neuroprosthesis for daily upper limb support.

BACKGROUND: MUNDUS is an assistive framework for recovering direct interaction capability of severely motor impaired people based on arm reaching and hand functions. It aims at achieving personalization, modularity and maximization of the user's direct involvement in assistive systems. To this, MUNDUS exploits any residual control of the end-user and can be adapted to the level of severity or to the progression of the disease allowing the user to voluntarily interact with the environment. MUNDUS target pathologies are high-level spinal cord injury (SCI) and neurodegenerative and genetic neuromuscular diseases, such as amyotrophic lateral sclerosis, Friedreich ataxia, and multiple sclerosis (MS). The system can be alternatively driven by residual voluntary muscular activation, head/eye motion, and brain signals. MUNDUS modularly combines an antigravity lightweight and non-cumbersome exoskeleton, closed-loop controlled Neuromuscular Electrical Stimulation for arm and hand motion, and potentially a motorized hand orthosis, for grasping interactive objects. METHODS: The definition of the requirements and of the interaction tasks were designed by a focus group with experts and a questionnaire with 36 potential end-users. RESULTS: The functionality of all modules has been successfully demonstrated. User's intention was detected with a 100% success. Averaging all subjects and tasks, the minimum evaluation score obtained was 1.13 ± 0.99 for the release of the handle during the drinking task, whilst all the other sub-actions achieved a mean value above 1.6. All users, but one, subjectively perceived the usefulness of the assistance and could easily control the system. Donning time ranged from 6 to 65 minutes, scaled on the configuration complexity. CONCLUSIONS: The MUNDUS platform provides functional assistance to daily life activities; the modules integration depends on the user's need, the functionality of the system have been demonstrated for all the possible configurations, and preliminary assessment of usability and acceptance is promising.

FUN-SIS: A Fully UNsupervised approach for Surgical Instrument Segmentation.

Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of a ground-truth supervision signal, obtained via manual annotation, thus expensive to collect at large scale. In this paper, we present FUN-SIS, a Fully-UNsupervised approach for binary Surgical Instrument Segmentation. FUN-SIS trains a per-frame segmentation model on completely unlabelled endoscopic videos, by solely relying on implicit motion information and instrument shape-priors. We define shape-priors as realistic segmentation masks of the instruments, not necessarily coming from the same dataset/domain as the videos. The shape-priors can be collected in various and convenient ways, such as recycling existing annotations from other datasets. We leverage them as part of a novel generative-adversarial approach, allowing to perform unsupervised instrument segmentation of optical-flow images during training. We then use the obtained instrument masks as pseudo-labels in order to train a per-frame segmentation model; to this aim, we develop a learning-from-noisy-labels architecture, designed to extract a clean supervision signal from these pseudo-labels, leveraging their peculiar noise properties. We validate the proposed contributions on three surgical datasets, including the MICCAI 2017 EndoVis Robotic Instrument Segmentation Challenge dataset. The obtained fully-unsupervised results for surgical instrument segmentation are almost on par with the ones of fully-supervised state-of-the-art approaches. This suggests the tremendous potential of the proposed method to leverage the great amount of unlabelled data produced in the context of minimally invasive surgery.

IMU-based classification of resistive exercises for real-time training monitoring on board the international space station with potential telemedicine spin-off.

The microgravity exposure that astronauts undergo during space missions lasting up to 6 months induces biochemical and physiological changes potentially impacting on their health. As a countermeasure, astronauts perform an in-flight training program consisting in different resistive exercises. To train optimally and safely, astronauts need guidance by on-ground specialists via a real-time audio/video system that, however, is subject to a communication delay that increases in proportion to the distance between sender and receiver. The aim of this work was to develop and validate a wearable IMU-based biofeedback system to monitor astronauts in-flight training displaying real-time feedback on exercises execution. Such a system has potential spin-offs also on personalized home/remote training for fitness and rehabilitation. 29 subjects were recruited according to their physical shape and performance criteria to collect kinematics data under ethical committee approval. Tests were conducted to (i) compare the signals acquired with our system to those obtained with the current state-of-the-art inertial sensors and (ii) to assess the exercises classification performance. The magnitude square coherence between the signals collected with the two different systems shows good agreement between the data. Multiple classification algorithms were tested and the best accuracy was obtained using a Multi-Layer Perceptron (MLP). MLP was also able to identify mixed errors during the exercise execution, a scenario that is quite common during training. The resulting system represents a novel low-cost training monitor tool that has space application, but also potential use on Earth for individuals working-out at home or remotely thanks to its ease of use and portability.

FRSR: Framework for real-time scene reconstruction in robot-assisted minimally invasive surgery.

3D reconstruction of the intra-operative scenes provides precise position information which is the foundation of various safety related applications in robot-assisted surgery, such as augmented reality. Herein, a framework integrated into a known surgical system is proposed to enhance the safety of robotic surgery. In this paper, we present a scene reconstruction framework to restore the 3D information of the surgical site in real time. In particular, a lightweight encoder-decoder network is designed to perform disparity estimation, which is the key component of the scene reconstruction framework. The stereo endoscope of da Vinci Research Kit (dVRK) is adopted to explore the feasibility of the proposed approach, and it provides the possibility for the migration to other Robot Operating System (ROS) based robot platforms due to the strong independence on hardware. The framework is evaluated using three different scenarios, including a public dataset (3018 pairs of endoscopic images), the scene from the dVRK endoscope in our lab as well as a self-made clinical dataset captured from an oncology hospital. Experimental results show that the proposed framework can reconstruct 3D surgical scenes in real time (25 FPS), and achieve high accuracy (2.69 ± 1.48 mm in MAE, 5.47 ± 1.34 mm in RMSE and 0.41 ± 0.23 in SRE, respectively). It demonstrates that our framework can reconstruct intra-operative scenes with high reliability of both accuracy and speed, and the validation of clinical data also shows its potential in surgery. This work enhances the state of art in 3D intra-operative scene reconstruction based on medical robot platforms. The clinical dataset has been released to promote the development of scene reconstruction in the medical image community.

Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma.

PURPOSE: Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance is of utmost importance as it has the potential to aid clinical decision-making. Though radiomics-based machine learning (ML) has demonstrated the promising performance in PCNSL, it demands large amounts of manual feature extraction efforts from magnetic resonance images beforehand. deep learning (DL) overcomes this limitation. METHODS: In this paper, we tailored the 3D ResNet to predict the OS of patients with PCNSL. To overcome the limitation of data sparsity, we introduced data augmentation and transfer learning, and we evaluated the results using r stratified k-fold cross-validation. To explain the results of our model, gradient-weighted class activation mapping was applied. RESULTS: We obtained the best performance (the standard error) on post-contrast T1-weighted (T1Gd)-area under curve [Formula: see text], accuracy [Formula: see text], precision [Formula: see text], recall [Formula: see text] and F1-score [Formula: see text], while compared with ML-based models on clinical data and radiomics data, respectively, further confirming the stability of our model. Also, we observed that PCNSL is a whole-brain disease and in the cases where the OS is less than 1 year, it is more difficult to distinguish the tumor boundary from the normal part of the brain, which is consistent with the clinical outcome. CONCLUSIONS: All these findings indicate that T1Gd can improve prognosis predictions of patients with PCNSL. To the best of our knowledge, this is the first time to use DL to explain model patterns in OS classification of patients with PCNSL. Future work would involve collecting more data of patients with PCNSL, or additional retrospective studies on different patient populations with rare diseases, to further promote the clinical role of our model.

Reaching while standing in microgravity: a new postural solution to oversimplify movement control.

Many studies showed that both arm movements and postural control are characterized by strong invariants. Besides, when a movement requires simultaneous control of the hand trajectory and balance maintenance, these two movement components are highly coordinated. It is well known that the focal and postural invariants are individually tightly linked to gravity, much less is known about the role of gravity in their coordination. It is not clear whether the effect of gravity on different movement components is such as to keep a strong movement-posture coordination even in different gravitational conditions or whether gravitational information is necessary for maintaining motor synergism. We thus set out to analyze the movements of eleven standing subjects reaching for a target in front of them beyond arm's length in normal conditions and in microgravity. The results showed that subjects quickly adapted to microgravity and were able to successfully accomplish the task. In contrast to the hand trajectory, the postural strategy was strongly affected by microgravity, so to become incompatible with normo-gravity balance constraints. The distinct effects of gravity on the focal and postural components determined a significant decrease in their reciprocal coordination. This finding suggests that movement-posture coupling is affected by gravity, and thus, it does not represent a unique hardwired and invariant mode of control. Additional kinematic and dynamic analyses suggest that the new motor strategy corresponds to a global oversimplification of movement control, fulfilling the mechanical and sensory constraints of the microgravity environment.

Error-enhancing robot therapy to induce motor control improvement in childhood onset primary dystonia.

BACKGROUND: Robot-generated deviating forces during multijoint reaching movements have been applied to investigate motor control and to tune neuromotor adaptation. Can the application of force to limbs improve motor learning? In this framework, the response to altered dynamic environments of children affected by primary dystonia has never been studied. METHODS: As preliminary pilot study, eleven children with primary dystonia and eleven age-matched healthy control subjects were asked to perform upper limb movements, triangle-reaching (three directions) and circle-writing, using a haptic robot interacting with ad-hoc developed task-specific visual interfaces. Three dynamic conditions were provided, null additive external force (A), constant disturbing force (B) and deactivation of the additive external force again (C). The path length for each trial was computed, from the recorded position data and interaction events. RESULTS: The results show that the disturbing force affects significantly the movement outcomes in healthy but not in dystonic subjects, already compromised in the reference condition: the external alteration uncalibrates the healthy sensorimotor system, while the dystonic one is already strongly uncalibrated. The lack of systematic compensation for perturbation effects during B condition is reflected into the absence of after-effects in C condition, which would be the evidence that CNS generates a prediction of the perturbing forces using an internal model of the environment.The most promising finding is that in dystonic population the altered dynamic exposure seems to induce a subsequent improvement, i.e. a beneficial after-effect in terms of optimal path control, compared with the correspondent reference movement outcome. CONCLUSIONS: The short-time error-enhancing training in dystonia could represent an effective approach for motor performance improvement, since the exposure to controlled dynamic alterations induces a refining of the existing but strongly imprecise motor scheme and sensorimotor patterns.

Accurate multi-robot targeting for keyhole neurosurgery based on external sensor monitoring.

Robotics has recently been introduced in surgery to improve intervention accuracy, to reduce invasiveness and to allow new surgical procedures. In this framework, the ROBOCAST system is an optically surveyed multi-robot chain aimed at enhancing the accuracy of surgical probe insertion during keyhole neurosurgery procedures. The system encompasses three robots, connected as a multiple kinematic chain (serial and parallel), totalling 13 degrees of freedom, and it is used to automatically align the probe onto a desired planned trajectory. The probe is then inserted in the brain, towards the planned target, by means of a haptic interface. This paper presents a new iterative targeting approach to be used in surgical robotic navigation, where the multi-robot chain is used to align the surgical probe to the planned pose, and an external sensor is used to decrease the alignment errors. The iterative targeting was tested in an operating room environment using a skull phantom, and the targets were selected on magnetic resonance images. The proposed targeting procedure allows about 0.3 mm to be obtained as the residual median Euclidean distance between the planned and the desired targets, thus satisfying the surgical accuracy requirements (1 mm), due to the resolution of the diffused medical images. The performances proved to be independent of the robot optical sensor calibration accuracy.

Robot-assisted ex vivo neobladder reconstruction: preliminary results of surgical skill evaluation.

PURPOSE: Advanced developments in the medical field have gradually increased the public demand for surgical skill evaluation. However, this assessment always depends on the direct observation of experienced surgeons, which is time-consuming and variable. The introduction of robot-assisted surgery provides a new possibility for this evaluation paradigm. This paper aims at evaluating surgeon performance automatically with novel evaluation metrics based on different surgical data. METHODS: Urologists ([Formula: see text]) from a hospital were requested to perform a simplified neobladder reconstruction on an ex vivo setup twice with different camera modalities ([Formula: see text]) randomly. They were divided into novices and experts ([Formula: see text], respectively) according to their experience in robot-assisted surgeries. Different performance metrics ([Formula: see text]) are proposed to achieve the surgical skill evaluation, considering both instruments and endoscope. Also, nonparametric tests are adopted to check if there are significant differences when evaluating surgeons performance. RESULTS: When grouping according to four stages of neobladder reconstruction, statistically significant differences can be appreciated in phase 1 ([Formula: see text]) and phase 2 ([Formula: see text]) with normalized time-related metrics and camera movement-related metrics, respectively. On the other hand, considering experience grouping shows that both metrics are able to highlight statistically significant differences between novice and expert performances in the control protocol. It also shows that the camera-related performance of experts is significantly different ([Formula: see text]) when handling the endoscope manually and when it is automatic. CONCLUSION: Surgical skill evaluation, using the approach in this paper, can effectively measure surgical procedures of surgeons with different experience. Preliminary results demonstrate that different surgical data can be fully utilized to improve the reliability of surgical evaluation. It also demonstrates its versatility and potential in the quantitative assessment of various surgical operations.

Cycling induced by electrical stimulation improves motor recovery in postacute hemiparetic patients: a randomized controlled trial.

BACKGROUND AND PURPOSE: This study assessed whether cycling induced by functional electrical stimulation (FES) was more effective than passive cycling with placebo stimulation in promoting motor recovery and walking ability in postacute hemiparetic patients. METHODS: In a double-blind, randomized, controlled trial, 35 patients were included and randomized to receive FES-induced cycling training or placebo FES cycling. The 4-week treatment consisted of 20 sessions lasting 25 minutes each. Primary outcome measures included the leg subscale of the Motricity Index and gait speed during a 50-meter walking test. Secondary outcomes were the Trunk Control Test, the Upright Motor Control Test, the mean work produced by the paretic leg, and the unbalance in mechanical work between paretic and nonparetic legs during voluntary pedaling. Participants were evaluated before training, after training, and at 3- to 5-month follow-up visits. RESULTS: No significant differences were found between groups at baseline. Repeated-measures ANOVA (P<0.05) revealed significant increases in Motricity Index, Trunk Control Test, Upright Motor Control Test, gait speed, and mean work of the paretic leg after training and at follow-up assessments for FES-treated patients. No outcome measures demonstrated significant improvements after training in the placebo group. Both groups showed no significant differences between assessments after training and at follow-up. A main effect favoring FES-treated patients was demonstrated by repeated-measures ANCOVA for Motricity Index (P<0.001), Trunk Control Test (P=0.001), Upright Motor Control Test (P=0.005), and pedaling unbalance (P=0.038). CONCLUSIONS: The study demonstrated that 20 sessions of FES cycling training significantly improved lower extremity motor functions and accelerated the recovery of overground locomotion in postacute hemiparetic patients. Improvements were maintained at follow-up.

Accurate calibration method for 3D freehand ultrasound probe using virtual plane.

PURPOSE: In this paper a new, easy-to-manufacture and easy-to-use ultrasound (US) probe calibration phantom for 3D freehand scanning is presented and evaluated, together with a new method for achieving an accurate and user-robust calibration using virtual plane. METHODS: The phantom allows the optically tracked US probe to perform two rotations and two translations while keeping the image of a tensioned wire in the image plane. This approach allows obtaining a sharp image of the wire independently from the probe pose. The virtual plane allows the calibration algorithm to converge minimizing the required number of US probe tracked poses. The US image and position data are synchronized via a CORBA interface, created within the Image Guided Surgery Toolkit (IGSTK) framework. The calibration algorithm and the calibration protocol were evaluated in a set of experiments carried out by different test-users. RESULTS: The calibration method proved to be accurate and precise: 3D point reconstruction accuracy resulted 0.2 mm as mean value, while the precision was 0.4 mm as standard deviation. CONCLUSIONS: The technique showed to be suitable for medical applications from morphological diagnosis to intraoperative surgical planning adaption.

A biofeedback cycling training to improve locomotion: a case series study based on gait pattern classification of 153 chronic stroke patients.

BACKGROUND: The restoration of walking ability is the main goal of post-stroke lower limb rehabilitation and different studies suggest that pedaling may have a positive effect on locomotion. The aim of this study was to explore the feasibility of a biofeedback pedaling treatment and its effects on cycling and walking ability in chronic stroke patients. A case series study was designed and participants were recruited based on a gait pattern classification of a population of 153 chronic stroke patients. METHODS: In order to optimize participants selection, a k-means cluster analysis was performed to subgroup homogenous gait patterns in terms of gait speed and symmetry.The training consisted of a 2-week treatment of 6 sessions. A visual biofeedback helped the subjects in maintaining a symmetrical contribution of the two legs during pedaling. Participants were assessed before, after training and at follow-up visits (one week after treatment). Outcome measures were the unbalance during a pedaling test, and the temporal, spatial, and symmetry parameters during gait analysis. RESULTS AND DISCUSSION: Three clusters, mainly differing in terms of gait speed, were identified and participants, representative of each cluster, were selected.An intra-subject statistical analysis (ANOVA) showed that all patients significantly decreased the pedaling unbalance after treatment and maintained significant improvements with respect to baseline at follow-up. The 2-week treatment induced some modifications in the gait pattern of two patients: one, the most impaired, significantly improved mean velocity and increased gait symmetry; the other one reduced significantly the over-compensation of the healthy limb. No benefits were produced in the gait of the last subject who maintained her slow but almost symmetrical pattern. Thus, this study might suggest that the treatment can be beneficial for patients having a very asymmetrical and inefficient gait and for those that overuse the healthy leg. CONCLUSION: The results demonstrated that the treatment is feasible and it might be effective in translating progresses from pedaling to locomotion. If these results are confirmed on a larger and controlled scale, the intervention, thanks to its safety and low price, could have a significant impact as a home- rehabilitation treatment for chronic stroke patients.