A System for Reproducible 3D Ultrasound Measurements of Skeletal Muscles.

In 3D freehand ultrasound imaging, operator dependent variations in applied forces and movements can lead to errors in the reconstructed images. In this paper, we introduce an automated 3D ultrasound system, which enables acquisitions with controlled movement trajectories by using motors, which electrically move the probe. Due to integrated encoders there is no need of position sensors. An included force control mechanism ensures a constant contact force to the skin. We conducted 8 trials with the automated 3D ultrasound system on 2 different phantoms with 3 force settings and 10 trials on a human tibialis anterior muscle with 2 force settings. For comparison, we also conducted 8 freehand 3D ultrasound scans from 2 operators (4 force settings) on one phantom and 10 with one operator on the tibialis anterior muscle. Both freehand and automated trials showed small errors in volume and length computations of the reconstructions, however the freehand trials showed larger standard deviations. We also computed the thickness of the phantom and the tibialis anterior muscle. We found significant differences in force settings for the operators and higher coefficients of variation for the freehand trials. Overall, the automated 3D ultrasound system shows a high accuracy in reconstruction. Due to the smaller coefficients of variation, the automated 3D ultrasound system enables more reproducible ultrasound examinations than the freehand scanning. Therefore, the automated 3D ultrasound system is a reliable tool for 3D investigations of skeletal muscle.

Deep-Learning Markerless Tracking of Infant General Movements using Standard Video Recordings.

Monitoring spontaneous General Movements (GM) of infants 6-20 weeks post-term age is a reliable tool to assess the quality of neurodevelopment in early infancy. Abnormal or absent GMs are reliable prognostic indicators of whether an infant is at risk of developing neurological impairments and disorders such as cerebral palsy (CP). Therapeutic interventions are most effective at improving neuromuscular outcomes if administered in early infancy. Current clinical protocols require trained assessors to rate videos of infant movements, a time-intensive task. This work proposes a simple, inexpensive, and broadly applicable markerless pose-estimation approach for automatic infant movement tracking using conventional video recordings from handheld devices (e.g., tablets and mobile phones). We leverage the enhanced capabilities of deep-learning technology in image processing to identify 12 anatomical locations (3 per limb) in each video frame, tracking a baby's natural movement throughout the recordings. We validate the capability of resnet152 and a mobile-net-v2-1 to identify body-parts in unseen frames from a full-term male infant, using a novel automatic unsupervised approach that fuses likelihood outputs of a Kalman filter and the deep-nets. Both deep-net models were found to perform very well in the identification of anatomical locations in the unseen data with high average Percentage of Correct Keypoints (aPCK) performances of >99.65% across all locations.Clinical relevance-Results of this research confirm the feasibility of a low-cost and publicly accessible technology to automatically track infants' GMs and diagnose those at higher risk of developing neurological conditions early, when clinical interventions are most effective.

Deciphering the "Art" in Modeling and Simulation of the Knee Joint: Assessing Model Calibration Workflows and Outcomes.

Model reproducibility is a point of emphasis for the National Institutes of Health (NIH) and in science, broadly. As the use of computational modeling in biomechanics and orthopedics grows, so does the need to assess the reproducibility of modeling workflows and simulation predictions. The long-term goal of the KneeHub project is to understand the influence of potentially subjective decisions, thus the modeler's "art", on the reproducibility and predictive uncertainty of computational knee joint models. In this paper, we report on the model calibration phase of this project, during which five teams calibrated computational knee joint models of the same specimens from the same specimen-specific joint mechanics dataset. We investigated model calibration approaches and decisions, and compared calibration workflows and model outcomes among the teams. The selection of the calibration targets used in the calibration workflow differed greatly between the teams and was influenced by modeling decisions related to the representation of structures, and considerations for computational cost and implementation of optimization. While calibration improved model performance, differences in the postcalibration ligament properties and predicted kinematics were quantified and discussed in the context of modeling decisions. Even for teams with demonstrated expertise, model calibration is difficult to foresee and plan in detail, and the results of this study underscore the importance of identification and standardization of best practices for data sharing and calibration.

Predicting ankle and knee sagittal kinematics and kinetics using an ankle-mounted inertial sensor.

The purpose of this study was to develop a machine learning model to reconstruct time series kinematic and kinetic profiles of the ankle and knee joint across six different tasks using an ankle-mounted IMU. Four male collegiate basketball players performed repeated tasks, including walking, jogging, running, sidestep cutting, max-height jumping, and stop-jumping, resulting in a total of 102 movements. Ankle and knee flexion-extension angles and moments were estimated using motion capture and inverse dynamics and considered 'actual data' for the purpose of model fitting. Synchronous acceleration and angular velocity data were collected from right ankle-mounted IMUs. A time-series feature extraction model was used to determine a set of features used as input to a random forest regression model to predict the ankle and knee kinematics and kinetics. Five-fold cross-validation was performed to verify the model accuracy, and statistical parametric mapping was used to determine the difference between the predicted and experimental time series. The random forest regression model predicted the time-series profiles of the ankle and knee flexion-extension angles and moments with high accuracy (Kinematics: R2 ranged from 0.782 to 0.962, RMSE ranged from 2.19° to 11.58°; Kinetics: R2 ranged from 0.711 to 0.966, RMSE ranged from 0.10 Nm/kg to 0.41 Nm/kg). There were differences between predicted and actual time series for the knee flexion-extension moment during stop-jumping and walking. An appropriately trained feature-based regression model can predict time series knee and ankle joint angles and moments across a wide range of tasks using a single ankle-mounted IMU.

Reproducibility in modeling and simulation of the knee: Academic, industry, and regulatory perspectives.

Stakeholders in the modeling and simulation (M&S) community organized a workshop at the 2019 Annual Meeting of the Orthopaedic Research Society (ORS) entitled "Reproducibility in Modeling and Simulation of the Knee: Academic, Industry, and Regulatory Perspectives." The goal was to discuss efforts among these stakeholders to address irreproducibility in M&S focusing on the knee joint. An academic representative from a leading orthopedic hospital in the United States described a multi-institutional, open effort funded by the National Institutes of Health to assess model reproducibility in computational knee biomechanics. A regulatory representative from the United States Food and Drug Administration indicated the necessity of standards for reproducibility to increase utility of M&S in the regulatory setting. An industry representative from a major orthopedic implant company emphasized improving reproducibility by addressing indeterminacy in personalized modeling through sensitivity analyses, thereby enhancing preclinical evaluation of joint replacement technology. Thought leaders in the M&S community stressed the importance of data sharing to minimize duplication of efforts. A survey comprised 103 attendees revealed strong support for the workshop and for increasing emphasis on computational modeling at future ORS meetings. Nearly all survey respondents (97%) considered reproducibility to be an important issue. Almost half of respondents (45%) tried and failed to reproduce the work of others. Two-thirds of respondents (67%) declared that individual laboratories are most responsible for ensuring reproducible research whereas 44% thought that journals are most responsible. Thought leaders and survey respondents emphasized that computational models must be reproducible and credible to advance knee M&S.

Assessment of reporting practices and reproducibility potential of a cohort of published studies in computational knee biomechanics.

Reproducible research serves as a pillar of the scientific method and is a foundation for scientific advancement. However, estimates for irreproducibility of preclinical science range from 75% to 90%. The importance of reproducible science has not been assessed in the context of mechanics-based modeling of human joints such as the knee, despite this being an area that has seen dramatic growth. Framed in the context of five experienced teams currently documenting knee modeling procedures, the aim of this study was to evaluate reporting and the perceived potential for reproducibility across studies the teams viewed as important contributions to the literature. A cohort of studies was selected by polling, which resulted in an assessment of nine studies as opposed to a broader analysis across the literature. Using a published checklist for reporting of modeling features, the cohort was evaluated for both "reporting" and their potential to be "reproduced," which was delineated into six major modeling categories and three subcategories. Logistic regression analysis revealed that for individual modeling categories, the proportion of "reported" occurrences ranged from 0.31, 95% confidence interval (CI) [0.23, 0.41] to 0.77, 95% CI: [0.68, 0.86]. The proportion of whether a category was perceived as "reproducible" ranged from 0.22, 95% CI: [0.15, 0.31] to 0.44, 95% CI: [0.35, 0.55]. The relatively low ratios highlight an opportunity to improve reporting and reproducibility of knee modeling studies. Ongoing efforts, including our findings, contribute to a dialogue that facilitates adoption of practices that provide both credibility and translation possibilities.

Predicting the hip joint centre in children: New regression equations, linear scaling, and statistical shape modelling.

Determination of the hip joint centre (HJC) is important to accurately estimate hip joint motion, moments and muscle forces. The most accurate method for HJC estimation without medical imaging is an area of interest in the biomechanics community, especially in a paediatric population, which has not been widely evaluated. HJC locations were calculated by sphere-fitting to the acetabulum of three-dimensional pelvises segmented from 333 CT scans of children aged 4 to 18 years old. Three methods for determining the HJC were compared: regression equations, linear scaling, and shape model prediction. The new regression equations developed in this study produced Euclidean distance errors of 6.23 mm ± 2.90 mm. Linear scaling of paediatric bone produced errors of 3.90 mm ± 2.52 mm and adult bone scaling of 5.45 mm ± 3.26 mm. Prediction of the HJC using a paediatric statistical shape model produced mean Euclidian distance errors of 2.95 mm ± 1.65 mm. Overall, shape model prediction of the HJC produced the lowest errors, with linear scaling of a mean paediatric pelvis providing better estimates than regression equations.

A Parameter Sensitivity Analysis on Multiple Finite Element Knee Joint Models.

The reproducibility of computational knee joint modeling is questionable, with models varying depending on the modeling team. The influence of model variations on simulation outcomes should be investigated, since knowing the sensitivity of the model outcomes to model parameters could help determine which parameters to calibrate and which parameters could potentially be standardized, improving model reproducibility. Previous sensitivity analyses on finite element knee joint models have typically used one model, with a few parameters and ligaments represented as line segments. In this study, a parameter sensitivity analysis was performed using multiple finite element knee joint models with continuum ligament representations. Four previously developed and calibrated models of the tibiofemoral joint were used. Parameters of the ligament and meniscus material models, the cartilage contact formulation, the simulation control and the rigid cylindrical joints were studied. Varus-valgus simulations were performed, changing one parameter at a time. The sensitivity on model convergence, valgus kinematics, articulating cartilage contact pressure and contact pressure location were investigated. A scoring system was defined to categorize the parameters as having a "large," "medium" or "small" influence on model output. Model outcomes were sensitive to the ligament prestretch factor, Young's modulus and attachment condition parameters. Changes in the meniscus horn stiffness had a "small" influence. Of the cartilage contact parameters, the penalty factor and Augmented Lagrangian setting had a "large" influence on the cartilage contact pressure. In the rigid cylindrical joint, the largest influence on the outcome parameters was found by the moment penalty parameter, which caused convergence issues. The force penalty and gap tolerance had a "small" influence at most. For the majority of parameters, the sensitivity was model-dependent. For example, only two models showed convergence issues when changing the Quasi-Newton update method. Due to the sensitivity of the model parameters being model-specific, the sensitivity of the parameters found in one model cannot be assumed to be the same in other models. The sensitivity of the model outcomes to ligament material properties confirms that calibration of these parameters is critical and using literature values may not be appropriate.

Hip Contact Force Magnitude and Regional Loading Patterns Are Altered in Those with Femoroacetabular Impingement Syndrome.

PURPOSE: The magnitude and location of hip contact force influence the local mechanical environment of the articular tissue, driving remodeling. We used a neuromusculoskeletal model to investigate hip contact force magnitudes and their regional loading patterns on the articular surfaces in those with femoroacetabular impingement (FAI) syndrome and controls during walking. METHODS: An EMG-assisted neuromusculoskeletal model was used to estimate hip contact forces in eligible participants with FAI syndrome ( n = 41) and controls ( n = 24), walking at self-selected speed. Hip contact forces were used to determine the average and spread of regional loading for femoral and acetabular articular surfaces. Hip contact force magnitude and region of loading were compared between groups using statistical parametric mapping and independent t -tests, respectively ( P < 0.05). RESULTS: All of the following findings are reported compared with controls. Those with FAI syndrome walked with lower-magnitude hip contact forces (mean difference, -0.7 N·BW -1 ; P < 0.001) during first and second halves of stance, and with lower anteroposterior, vertical, and mediolateral contact force vector components. Participants with FAI syndrome also had less between-participant variation in average regional loading, which was located more anteriorly (3.8°, P = 0.035) and laterally (2.2°, P = 0.01) on the acetabulum but more posteriorly (-4.8°, P = 0.01) on the femoral head. Participants with FAI syndrome had a smaller spread of regional loading across both the acetabulum (-1.9 mm, P = 0.049) and femoral head (1 mm, P < 0.001) during stance. CONCLUSIONS: Compared with controls, participants with FAI syndrome walked with lower-magnitude hip contact forces that were constrained to smaller regions on the acetabulum and femoral head. Differences in regional loading patterns might contribute to the mechanobiological processes driving cartilage maladaptation in those with FAI syndrome.

A statistical shape model of soleus muscle morphology in spastic cerebral palsy.

This study investigated morphological characteristics of the soleus muscle in cerebral palsy (CP) and typically developing (TD) cohorts using a statistical shape model and differentiated dominant features between the two cohorts. We generated shape models of CP and TD cohorts to characterize dominant features within each. We then generated a combined shape model of both CP and TD to assess deviations of the cohorts' soleuses from a common mean shape, and statistically analysed differences between the cohorts. The shape models revealed similar principal components (PCs) with different variance between groups. The CP shape model yielded a distinct feature (superior-inferior shift of the broad central region) accounting for 8.1% of the model's cumulative variance. The combined shape model presented two PCs where differences arose between CP and TD cohorts: size and aspect ratio of length-width-thickness. The distinct appearance characteristic in the CP model-described above-may implicate impaired muscle function in children with CP. Overall, children with CP had smaller muscles that also tended to be long, thin, and narrow. Shape modelling captures dominant morphological features of structures, which was used here to quantitatively describe CP muscles and further probe our understanding of the disease's impact on the muscular system.

Morphological variation in paediatric lower limb bones.

Available methods for generating paediatric musculoskeletal geometry are to scale generic adult geometry, which is widely accessible but can be inaccurate, or to obtain geometry from medical imaging, which is accurate but time-consuming and costly. A population-based shape model is required to generate accurate and accessible musculoskeletal geometry in a paediatric population. The pelvis, femur, and tibia/fibula were segmented from 333 CT scans of children aged 4-18 years. Bone morphology variation was captured using principal component analysis (PCA). Subsequently, a shape model was developed to predict bone geometry from demographic and linear bone measurements and validated using a leave one out analysis. The shape model was compared to linear scaling of adult and paediatric bone geometry. The PCA captured growth-related changes in bone geometry. The shape model predicted bone geometry with root mean squared error (RMSE) of 2.91 ± 0.99 mm in the pelvis, 2.01 ± 0.62 mm in the femur, and 1.85 ± 0.54 mm in the tibia/fibula. Linear scaling of an adult mesh produced RMSE of 4.79 ± 1.39 mm in the pelvis, 4.38 ± 0.72 mm in the femur, and 4.39 ± 0.86 mm in the tibia/fibula. We have developed a method for capturing and predicting lower limb bone shape variation in a paediatric population more accurately than linear scaling without using medical imaging.

Free Achilles tendon strain during selected rehabilitation, locomotor, jumping, and landing tasks.

A better understanding of the strains experienced by the Achilles tendon during commonly prescribed exercises and locomotor tasks is needed to improve efficacy of Achilles tendon training and rehabilitation programs. The aim of this study was to estimate in vivo free Achilles tendon strain during selected rehabilitation, locomotor, jumping, and landing tasks. Sixteen trained runners with no symptoms of Achilles tendinopathy participated in this study. Personalized free Achilles tendon moment arm and force-strain curve were obtained from imaging data and used in conjunction with motion capture and surface electromyography to estimate free Achilles tendon strain using electromyogram-informed neuromusculoskeletal modeling. There was a strong correspondence between Achilles tendon force estimates from the present study and experimental data reported in the literature (R2 > 0.85). The average tendon strain was highest for maximal hop landing (8.8 ± 1.6%), lowest for walking at 1.4 m/s (3.1 ± 0.8%), and increased with locomotor speed during running (run 3.0 m/s: 6.5 ± 1.6%; run 5.0 m/s: 7.9 ± 1.7%) and during heel rise exercise with added mass (BW: 5.8 ± 1.3%; 1.2 BW: 6.9 ± 1.7%). The peak tendon strain was highest during running (5 m/s: 13.7 ± 2.5%) and lowest during walking (1.4 m/s: 7 ± 1.8%). Overall findings provide a preliminary evidence base for exercise selection to maximize anabolic tendon remodeling during training and rehabilitation of the Achilles tendon.NEW & NOTEWORTHY Our work combines medical imaging and electromyogram-informed neuromusculoskeletal modeling data to estimate free Achilles tendon strain during selected rehabilitation, locomotor, jumping, and landing tasks in trained middle-distance runners. These data may potentially be used to inform Achilles tendon training and rehabilitation to maximize anabolic tendon remodeling.

Remote Patient Monitoring with Wearable Sensors Following Knee Arthroplasty.

(Background) Inertial Measurement Units (IMUs) provide a low-cost, portable solution to obtain functional measures similar to those captured with three-dimensional gait analysis, including spatiotemporal gait characteristics. The primary aim of this study was to determine the feasibility of a remote patient monitoring (RPM) workflow using ankle-worn IMUs measuring impact load, limb impact load asymmetry and knee range of motion in combination with patient-reported outcome measures. (Methods) A pilot cohort of 14 patients undergoing primary knee arthroplasty for osteoarthritis was prospectively enrolled. RPM in the community was performed weekly from 2 up to 6 weeks post-operatively using wearable IMUs. The following data were collected using IMUs: mobility (Bone Stimulus and cumulative impact load), impact load asymmetry and maximum knee flexion angle. In addition, scores from the Oxford Knee Score (OKS), EuroQol Five-dimension (EQ-5D) with EuroQol visual analogue scale (EQ-VAS) and 6 Minute Walk Test were collected. (Results) On average, the Bone Stimulus and cumulative impact load improved 52% (p = 0.002) and 371% (p = 0.035), compared to Post-Op Week 2. The impact load asymmetry value trended (p = 0.372) towards equal impact loading between the operative and non-operative limb. The mean maximum flexion angle achieved was 99.25° at Post-Operative Week 6, but this was not significantly different from pre-operative measurements (p = 0.1563). There were significant improvements in the mean EQ-5D (0.20; p = 0.047) and OKS (10.86; p < 0.001) scores both by 6 weeks after surgery, compared to pre-operative scores. (Conclusions) This pilot study demonstrates the feasibility of a reliable and low-maintenance workflow system to remotely monitor post-operative progress in knee arthroplasty patients. Preliminary data indicate IMU outputs relating to mobility, impact load asymmetry and range of motion can be obtained using commercially available IMU sensors. Further studies are required to directly correlate the IMU sensor outputs with patient outcomes to establish clinical significance.

Computational fluid dynamics simulations for 3D muscle fiber architecture in finite element analysis: Comparisons between computational fluid dynamics and diffusion tensor imaging.

Knowledge of skeletal muscle fiber orientations is important for modeling mechanical properties and behavior of muscle tissue. Diffusion tensor imaging (DTI) may be used to define fiber architecture in vivo but can be expensive and time-consuming and thus impractical for biomechanical modeling applications. Muscle tractography using computational fluid dynamics (CFD) has been shown to determine muscle fiber directions for finite element models in which aponeuroses serve as inlet and outlet boundaries. While the technique is simple to implement, it is unclear which flow simulations and constraints achieve fiber architectures similar to DTI and whether FE simulations based on CFD versus DTI fiber directions produce similar results. Here, we implement CFD tractography on the gastrocnemius muscle using a novel boundary condition method that we developed based on specified inflow direction. We compared results from incompressible potential flow and nondimensionalized incompressible Stokes flow. Comparisons were made between flow methods and results from DTI. Mechanical finite element simulations were subsequently performed on muscle models with fiber directions defined by CFD tractography and DTI. Using our boundary condition method, fiber directions modeled from CFD simulations were similar to DTI. Strain distributions from mechanical simulations were similar between Stokes flow and DTI fiber models. This study demonstrates a new method for specifying inlet boundary conditions that generates physiologically reasonable fiber directions in skeletal muscle. Finite element simulations based on this method are similar to those from DTI, illustrating the ability of CFD to determine muscle fiber architecture for modeling purposes when DTI is not available.

Correction: A marker registration method to improve joint angles computed by constrained inverse kinematics.

[This corrects the article DOI: 10.1371/journal.pone.0252425.].

A marker registration method to improve joint angles computed by constrained inverse kinematics.

Accurate computation of joint angles from optical marker data using inverse kinematics methods requires that the locations of markers on a model match the locations of experimental markers on participants. Marker registration is the process of positioning the model markers so that they match the locations of the experimental markers. Markers are typically registered using a graphical user interface (GUI), but this method is subjective and may introduce errors and uncertainty to the calculated joint angles and moments. In this investigation, we use OpenSim to isolate and quantify marker registration-based error from other sources of error by analyzing the gait of a bipedal humanoid robot for which segment geometry, mass properties, and joint angles are known. We then propose a marker registration method that is informed by the orientation of anatomical reference frames derived from surface-mounted optical markers as an alternative to user registration using a GUI. The proposed orientation registration method reduced the average root-mean-square error in both joint angles and joint moments by 67% compared to the user registration method, and eliminated variability among users. Our results show that a systematic method for marker registration that reduces subjective user input can make marker registration more accurate and repeatable.

A Method to Compare Heterogeneous Types of Bone and Cartilage Meshes.

Accurately capturing the bone and cartilage morphology and generating a mesh remains a critical step in the workflow of computational knee joint modeling. Currently, there is no standardized method to compare meshes of different element types and nodal densities, making comparisons across research teams a significant challenge. The aim of this paper is to describe a method to quantify differences in knee joint bone and cartilages meshes, independent of bone and cartilage mesh topology. Bone mesh-to-mesh distances, subchondral bone boundaries, and cartilage thicknesses from meshes of any type of mesh are obtained using a series of steps involving registration, resampling, and radial basis function fitting after which the comparisons are performed. Subchondral bone boundaries and cartilage thicknesses are calculated and visualized in a common frame of reference for comparison. The established method is applied to models developed by five modeling teams. Our approach to obtain bone mesh-to-mesh distances decreased the divergence seen in selecting a reference mesh (i.e., comparing mesh A-to-B versus mesh B-to-A). In general, the bone morphology was similar across teams. The cartilage thicknesses for all models were calculated and the mean absolute cartilage thickness difference was presented, the articulating areas had the best agreement across teams. The teams showed disagreement on the subchondral bone boundaries. The method presented in this paper allows for objective comparisons of bone and cartilage geometry that is agnostic to mesh type and nodal density.

Deciphering the "Art" in Modeling and Simulation of the Knee Joint: Variations in Model Development.

The use of computational modeling to investigate knee joint biomechanics has increased exponentially over the last few decades. Developing computational models is a creative process where decisions have to be made, subject to the modelers' knowledge and previous experiences, resulting in the "art" of modeling. The long-term goal of the KneeHub project is to understand the influence of subjective decisions on the final outcomes and the reproducibility of computational knee joint models. In this paper, we report on the model development phase of this project, investigating model development decisions and deviations from initial modeling plans. Five teams developed computational knee joint models from the same dataset, and we compared each teams' initial uncalibrated models and their model development workflows. Variations in the software tools and modeling approaches were found, resulting in differences such as the representation of the anatomical knee joint structures in the model. The teams consistently defined the boundary conditions and used the same anatomical coordinate system convention. However, deviations in the anatomical landmarks used to define the coordinate systems were present, resulting in a large spread in the kinematic outputs of the uncalibrated models. The reported differences and similarities in model development and simulation presented here illustrate the importance of the "art" of modeling and how subjective decision-making can lead to variation in model outputs. All teams deviated from their initial modeling plans, indicating that model development is a flexible process and difficult to plan in advance, even for experienced teams.

3D trunk orientation measured using inertial measurement units during anatomical and dynamic sports motions.

Trunk motion is related to the performance and risk of injuries during dynamic sports motions. Optical motion capture is traditionally used to measure trunk motion during dynamic sports motions, but these systems are typically constrained to a laboratory environment. Inertial measurement units (IMUs) might provide a suitable alternative for measuring the trunk orientation during dynamic sports motions. The objective of the present study was to assess the accuracy of the three-dimensional trunk orientation measured using IMUs during dynamic sports motions and isolated anatomical trunk motions. The motions were recorded with two IMUs and an optical motion capture system (gold standard). Ten participants performed a total of 71 sports motions (19 golf swings, 15 one-handed ball throws, 19 tennis serves, and 18 baseball swings) and 125 anatomical trunk motions (42, 41, and 42 trials of lateral flexion, axial rotation, and flexion/extension, respectively). The root-mean-square differences between the IMU- and optical motion capture-based trunk angles were less than 5 degrees, and the similarity between the methods was on average across all trials "very good" to "excellent" (R ≥ 0.85; R2 ≥ 0.80). Across the dynamic sports motions, even higher measures of similarity were found (R ≥ 0.90; R2 ≥ 0.82). When aligned to the relevant segment, the current IMUs are a promising alternative to optical motion capture and previous presented IMU-based systems for the field-based measurement of the three-dimensional trunk orientation during dynamic sports motions and the anatomical trunk motions.

Ankle torque forecasting using time-delayed neural networks.

A method for ankle torque prediction ahead of the current time is proposed in this paper. The mean average value of EMG signals from four muscles, alongside the joint angle and angular velocity of the right ankle, were used as input parameters to train a time-delayed artificial neural network. Data collected from five healthy subjects were used to generate the dataset to train and test the model. The model predicted ankle torque for five different future times from zero to 2 seconds. Model predictions were compared to torque calculated from inverse dynamics for each subject. The model predicted ankle torque up to 1 second ahead of time with normalized root mean squared error of less than 15 percent while the coefficient of determination was over 0.85.Clinical Relevance- the potential of the model for predicting joint torque ahead of time is helpful to establish an intuitive interaction between human and assistive robots. This model has application to assist patients with neurological disorders.