Inclusion of a skeletal model partly improves the reliability of lower limb joint angles derived from a markerless depth camera.

A single depth camera provides a fast and easy approach to performing biomechanical assessments in a clinical setting; however, there are currently no established methods to reliably determine joint angles from these devices. The primary aim of this study was to compare joint angles as well as the between-day reliability of direct kinematics to model-constrained inverse kinematics recorded using a single markerless depth camera during a range of clinical and athletic movement assessments.A secondary aim was to determine the minimum number of trials required to maximize reliability. Eighteen healthy participants attended two testing sessions one week apart. Tasks included treadmill walking, treadmill running, single-leg squats, single-leg countermovement jumps, bilateral countermovement jumps, and drop vertical jumps. Keypoint data were processed using direct kinematics as well as in OpenSim using a full-body musculoskeletal model and inverse kinematics. Kinematic methods were compared using statistical parametric mapping and between-day reliability was calculated using intraclass correlation coefficients, mean absolute error, and minimal detectable change. Keypoint-derived inverse kinematics resulted in significantly smaller hip flexion (range = -9 to -2°), hip abduction (range = -3 to -2°), knee flexion (range = -5° to -2°), and greater dorsiflexion angles (range = 6-15°) than direct kinematics. Both markerless kinematic methods had high between-day reliability (inverse kinematics ICC 95 %CI = 0.83-0.90; direct kinematics ICC 95 %CI = 0.80-0.93). For certain tasks and joints, keypoint-derived inverse kinematics resulted in greater reliability (up to 0.47 ICC) and smaller minimal detectable changes (up to 13°) than direct kinematics. Performing 2-4 trials was sufficient to maximize reliability for most tasks. A single markerless depth camera can reliably measure lower limb joint angles, and skeletal model-constrained inverse kinematics improves lower limb joint angle reliability for certain tasks and joints.

Prediction of Achilles Tendon Force During Common Motor Tasks From Markerless Video.

Remodeling of the Achilles tendon (AT) is partly driven by its mechanical environment. AT force can be estimated with neuromusculoskeletal (NMSK) modeling; however, the complex experimental setup required to perform the analyses confines use to the laboratory. We developed task-specific long short-term memory (LSTM) neural networks that employ markerless video data to predict the AT force during walking, running, countermovement jump, single-leg landing, and single-leg heel rise. The task-specific LSTM models were trained on pose estimation keypoints and corresponding AT force data from 16 subjects, calculated via an established NMSK modeling pipeline, and cross-validated using a leave-one-subject-out approach. As proof-of-concept, new motion data of one participant was collected with two smartphones and used to predict AT forces. The task-specific LSTM models predicted the time-series AT force using synthesized pose estimation data with root mean square error (RMSE) ≤ 526 N, normalized RMSE (nRMSE) ≤ 0.21 , R 2 ≥ 0.81 . Walking task resulted the most accurate with RMSE = 189±62 N; nRMSE = 0.11±0.03 , R 2 = 0.92±0.04 . AT force predicted with smartphones video data was physiologically plausible, agreeing in timing and magnitude with established force profiles. This study demonstrated the feasibility of using low-cost solutions to deploy complex biomechanical analyses outside the laboratory.

Hip contact forces can be predicted with a neural network using only synthesised key points and electromyography in people with hip osteoarthritis.

OBJECTIVE: To develop and validate a neural network to estimate hip contact forces (HCF), and lower body kinematics and kinetics during walking in individuals with hip osteoarthritis (OA) using synthesised anatomical key points and electromyography. To assess the capability of the neural network to detect directional changes in HCF resulting from prescribed gait modifications. DESIGN: A calibrated electromyography-informed neuromusculoskeletal model was used to compute lower body joint angles, moments, and HCF for 17 participants with mild-to-moderate hip OA. Anatomical key points (e.g., joint centres) were synthesised from marker trajectories and augmented with bias and noise expected from computer vision-based pose estimation systems. Temporal convolutional and long short-term memory neural networks (NN) were trained using leave-one-subject-out validation to predict neuromusculoskeletal modelling outputs from the synthesised key points and measured electromyography data from 5 hip-spanning muscles. RESULTS: HCF was predicted with an average error of 13.4 ± 7.1% of peak force. Joint angles and moments were predicted with an average root-mean-square-error of 5.3 degrees and 0.10 Nm/kg, respectively. The NN could detect changes in peak HCF that occur due to gait modifications with good agreement with neuromusculoskeletal modelling (r2 = 0.72) and a minimum detectable change of 9.5%. CONCLUSION: The developed neural network predicted HCF and lower body joint angles and moments in individuals with hip OA using noisy synthesised key point locations with acceptable errors. Changes in HCF magnitude due to gait modifications were predicted with high accuracy. These findings have important implications for implementation of load-modification based gait retraining interventions for people with hip OA in a natural environment (i.e., home, clinic).

Predicting Free Achilles Tendon Strain From Motion Capture Data Using Artificial Intelligence.

The Achilles tendon (AT) is sensitive to mechanical loading, with appropriate strain improving tissue mechanical and material properties. Estimating free AT strain is currently possible through personalized neuromusculoskeletal (NMSK) modeling; however, this approach is time-consuming and requires extensive laboratory data. To enable in-field assessments, we developed an artificial intelligence (AI) workflow to predict free AT strain during running from motion capture data. Ten keypoints commonly used in pose estimation algorithms (e.g., OpenPose) were synthesized from motion capture data and noise was added to represent real-world data obtained using video cameras. Two AI workflows were compared: (1) a Long Short-Term Memory (LSTM) neural network that predicted free AT strain directly (called LSTM only workflow); and (2) an LSTM neural network that predicted AT force which was subsequently converted to free AT strain using a personalized force-strain curve (called LSTM+ workflow). AI models were trained and evaluated using estimates of free AT strain obtained from a validated NMSK model with personalized AT force-strain curve. The effect of using different input features (position, velocity, and acceleration of keypoints, height and mass) on free AT strain predictions was also assessed. The LSTM+ workflow significantly improved the predictions of free AT strain compared to the LSTM only workflow (p < 0.001). The best free AT strain predictions were obtained using positions and velocities of keypoints as well as the height and mass of the participants as input, with average time-series root mean square error (RMSE) of 1.72±0.95% strain and r2 of 0.92±0.10, and peak strain RMSE of 2.20% and r2 of 0.54. In conclusion, we showed feasibility of predicting accurate free AT strain during running using low fidelity pose estimation data.

Maintaining soldier musculoskeletal health using personalised digital humans, wearables and/or computer vision.

OBJECTIVES: The physical demands of military service place soldiers at risk of musculoskeletal injuries and are major concerns for military capability. This paper outlines the development new training technologies to prevent and manage these injuries. DESIGN: Narrative review. METHODS: Technologies suitable for integration into next-generation training devices were examined. We considered the capability of technologies to target tissue level mechanics, provide appropriate real-time feedback, and their useability in-the-field. RESULTS: Musculoskeletal tissues' health depends on their functional mechanical environment experienced in military activities, training and rehabilitation. These environments result from the interactions between tissue motion, loading, biology, and morphology. Maintaining health of and/or repairing joint tissues requires targeting the "ideal" in vivo tissue mechanics (i.e., loading and strain), which may be enabled by real-time biofeedback. Recent research has shown that these biofeedback technologies are possible by integrating a patient's personalised digital twin and wireless wearable devices. Personalised digital twins are personalised neuromusculoskeletal rigid body and finite element models that work in real-time by code optimisation and artificial intelligence. Model personalisation is crucial in obtaining physically and physiologically valid predictions. CONCLUSIONS: Recent work has shown that laboratory-quality biomechanical measurements and modelling can be performed outside the laboratory with a small number of wearable sensors or computer vision methods. The next stage is to combine these technologies into well-designed easy to use products.

Feasibility of personalised hip load modification using real-time biofeedback in hip osteoarthritis: A pilot study.

Objective: (i) Compare the feasibility of three load modification strategies to immediately increase hip contact force in people with hip osteoarthritis (OA) using real-time visual biofeedback during walking, and (ii) prospectively evaluate changes in pain and physical function following 6-weeks of walking using a prescribed personalised load modification strategy. Design: Twenty participants with symptomatic mild-to-moderate hip OA walked on an instrumented treadmill while motion capture and electromyographic data were recorded (normal walk), then under three conditions: (i)neutral trunk lean; (ii)neutral pelvic obliquity; (iii)increased step length. The biomechanical parameter of interest and corresponding target value were displayed in real-time. Hip contact forces were subsequently computed using a calibrated electromyography-informed neuromusculoskeletal model. A decision tree was used to prescribe a personalised load modification strategy to each participant for integration into walking over 6-weeks. Results: Only the step length modification significantly increased peak hip contact force compared to normal walking when performed by all participants (11.34 [95%CI 4.54,18.13]%, P â€‹< â€‹0.01). After participants were prescribed a personalised load modification strategy, both neutral pelvis (n â€‹= â€‹5, 11.88[95%CI -0.49,24.24]%) and step length (n â€‹= â€‹10, 12.79[95%CI 0.49,25.09]%) subgroups increased peak hip contact force >10%. After 6-weeks, 77% and 46% of participants reported a clinically important improvement in hip pain during walking and physical function, respectively. Conclusion: Most participants with hip OA could immediately increase hip contact force through personalised movement retraining by a magnitude estimated to promote cartilage heath and reported an improvement in symptoms after 6-weeks. Findings provide preliminary support for a personalised load modification-based intervention for hip OA.

Multi-level personalization of neuromusculoskeletal models to estimate physiologically plausible knee joint contact forces in children.

Neuromusculoskeletal models are a powerful tool to investigate the internal biomechanics of an individual. However, commonly used neuromusculoskeletal models are generated via linear scaling of generic templates derived from elderly adult anatomies and poorly represent a child, let alone children with a neuromuscular disorder whose musculoskeletal structures and muscle activation patterns are profoundly altered. Model personalization can capture abnormalities and appropriately describe the underlying (altered) biomechanics of an individual. In this work, we explored the effect of six different levels of neuromusculoskeletal model personalization on estimates of muscle forces and knee joint contact forces to tease out the importance of model personalization for normal and abnormal musculoskeletal structures and muscle activation patterns. For six children, with and without cerebral palsy, generic scaled models were developed and progressively personalized by (1) tuning and calibrating musculotendon units' parameters, (2) implementing an electromyogram-assisted approach to synthesize muscle activations, and (3) replacing generic anatomies with image-based bony geometries, and physiologically and physically plausible muscle kinematics. Biomechanical simulations of gait were performed in the OpenSim and CEINMS software on ten overground walking trials per participant. A mixed-ANOVA test, with Bonferroni corrections, was conducted to compare all models' estimates. The model with the highest level of personalization produced the most physiologically plausible estimates. Model personalization is crucial to produce physiologically plausible estimates of internal biomechanical quantities. In particular, personalization of musculoskeletal anatomy and muscle activation patterns had the largest effect overall. Increased research efforts are needed to ease the creation of personalized neuromusculoskeletal models.

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.

The Free Achilles Tendon Is Shorter, Stiffer, Has Larger Cross-Sectional Area and Longer T2* Relaxation Time in Trained Middle-Distance Runners Compared to Healthy Controls.

Tendon geometry and tissue properties are important determinants of tendon function and injury risk and are altered in response to ageing, disease, and physical activity levels. The purpose of this study was to compare free Achilles tendon geometry and mechanical properties between trained elite/sub-elite middle-distance runners and a healthy control group. Magnetic resonance imaging (MRI) was used to measure free Achilles tendon volume, length, average cross-sectional area (CSA), regional CSA, moment arm, and T2* relaxation time at rest, while freehand three-dimensional ultrasound (3DUS) was used to quantify free Achilles tendon mechanical stiffness, Young's modulus, and length normalised mechanical stiffness. The free Achilles tendon in trained runners was significantly shorter and the average and regional CSA (distal end) were significantly larger compared to the control group. Mechanical stiffness of the free Achilles tendon was also significantly higher in trained runners compared to controls, which was explained by the group differences in tendon CSA and length. T2* relaxation time was significantly longer in trained middle-distance runners when compared to healthy controls. There was no relationship between T2* relaxation time and Young's modulus. The longer T2* relaxation time in trained runners may be indicative of accumulated damage, disorganised collagen, and increased water content in the free Achilles tendon. A short free Achilles tendon with large CSA and higher mechanical stiffness may enable trained runners to rapidly transfer high muscle forces and possibly reduce the risk of tendon damage from mechanical fatigue.

Targeted Achilles Tendon Training and Rehabilitation Using Personalized and Real-Time Multiscale Models of the Neuromusculoskeletal System.

Musculoskeletal tissues, including tendons, are sensitive to their mechanical environment, with both excessive and insufficient loading resulting in reduced tissue strength. Tendons appear to be particularly sensitive to mechanical strain magnitude, and there appears to be an optimal range of tendon strain that results in the greatest positive tendon adaptation. At present, there are no tools that allow localized tendon strain to be measured or estimated in training or a clinical environment. In this paper, we first review the current literature regarding Achilles tendon adaptation, providing an overview of the individual technologies that so far have been used in isolation to understand in vivo Achilles tendon mechanics, including 3D tendon imaging, motion capture, personalized neuromusculoskeletal rigid body models, and finite element models. We then describe how these technologies can be integrated in a novel framework to provide real-time feedback of localized Achilles tendon strain during dynamic motor tasks. In a proof of concept application, Achilles tendon localized strains were calculated in real-time for a single subject during walking, single leg hopping, and eccentric heel drop. Data was processed at 250 Hz and streamed on a smartphone for visualization. Achilles tendon peak localized strains ranged from ∼3 to ∼11% for walking, ∼5 to ∼15% during single leg hop, and ∼2 to ∼9% during single eccentric leg heel drop, overall showing large strain variation within the tendon. Our integrated framework connects, across size scales, knowledge from isolated tendons and whole-body biomechanics, and offers a new approach to Achilles tendon rehabilitation and training. A key feature is personalization of model components, such as tendon geometry, material properties, muscle geometry, muscle-tendon paths, moment arms, muscle activation, and movement patterns, all of which have the potential to affect tendon strain estimates. Model personalization is important because tendon strain can differ substantially between individuals performing the same exercise due to inter-individual differences in these model components.

Non-negative matrix factorisation is the most appropriate method for extraction of muscle synergies in walking and running.

Muscle synergies provide a simple description of a complex motor control mechanism. Synergies are extracted from muscle activation patterns using factorisation methods. Despite the availability of several factorisation methods in the literature, the most appropriate method for muscle synergy extraction is currently unknown. In this study, we compared four muscle synergy extraction methods: non-negative matrix factorisation, principal component analysis, independent component analysis, and factor analysis. Probability distribution of muscle activation patterns were compared with the probability distribution of synergy excitation primitives obtained from the four factorisation methods. Muscle synergies extracted using non-negative matrix factorisation best matched the probability distribution of muscle activation patterns across different walking and running speeds. Non-negative matrix factorisation also best tracked changes in muscle activation patterns compared to the other factorisation methods. Our results suggest that non-negative matrix factorisation is the best factorisation method for identifying muscle synergies in dynamic tasks with different levels of muscle contraction.

Development and validation of statistical shape models of the primary functional bone segments of the foot.

INTRODUCTION: Musculoskeletal models are important tools for studying movement patterns, tissue loading, and neuromechanics. Personalising bone anatomy within models improves analysis accuracy. Few studies have focused on personalising foot bone anatomy, potentially incorrectly estimating the foot's contribution to locomotion. Statistical shape models have been created for a subset of foot-ankle bones, but have not been validated. This study aimed to develop and validate statistical shape models of the functional segments in the foot: first metatarsal, midfoot (second-to-fifth metatarsals, cuneiforms, cuboid, and navicular), calcaneus, and talus; then, to assess reconstruction accuracy of these shape models using sparse anatomical data. METHODS: Magnetic resonance images of 24 individuals feet (age = 28 ± 6 years, 52% female, height = 1.73 ± 0.8 m, mass = 66.6 ± 13.8 kg) were manually segmented to generate three-dimensional point clouds. Point clouds were registered and analysed using principal component analysis. For each bone segment, a statistical shape model and principal components were created, describing population shape variation. Statistical shape models were validated by assessing reconstruction accuracy in a leave-one-out cross validation. Statistical shape models were created by excluding a participant's bone segment and used to reconstruct that same excluded bone using full segmentations and sparse anatomical data (i.e. three discrete points on each segment), for all combinations in the dataset. Tali were not reconstructed using sparse anatomical data due to a lack of externally accessible landmarks. Reconstruction accuracy was assessed using Jaccard index, root mean square error (mm), and Hausdorff distance (mm). RESULTS: Reconstructions generated using full segmentations had mean Jaccard indices between 0.77 ± 0.04 and 0.89 ± 0.02, mean root mean square errors between 0.88 ± 0.19 and 1.17 ± 0.18 mm, and mean Hausdorff distances between 2.99 ± 0.98 mm and 6.63 ± 3.68 mm. Reconstructions generated using sparse anatomical data had mean Jaccard indices between 0.67 ± 0.06 and 0.83 ± 0.05, mean root mean square error between 1.21 ± 0.54 mm and 1.66 ± 0.41 mm, and mean Hausdorff distances between 3.21 ± 0.94 mm and 7.19 ± 3.54 mm. Jaccard index was higher (P < 0.01) and root mean square error was lower (P < 0.01) in reconstructions from full segmentations compared to sparse anatomical data. Hausdorff distance was lower (P < 0.01) for midfoot and calcaneus reconstructions using full segmentations compared to sparse anatomical data. CONCLUSION: For the first time, statistical shape models of the primary functional segments of the foot were developed and validated. Foot segments can be reconstructed with minimal error using full segmentations and sparse anatomical landmarks. In future, larger training datasets could increase statistical shape model robustness, extending use to paediatric or pathological populations.

Magnetic Resonance Imaging and Freehand 3-D Ultrasound Provide Similar Estimates of Free Achilles Tendon Shape and 3-D Geometry.

The purpose of this study was to assess the similarity of free Achilles tendon shape and 3-D geometry between magnetic resonance imaging (MRI) and freehand 3-D ultrasound (3-DUS) imaging methods. Fourteen elite/sub-elite middle-distance runners participated in the study. MRI and 3-DUS scans of the Achilles tendon were acquired on two separate imaging sessions, and all 3-D reconstructions were performed using identical methods. Shape similarity of free Achilles tendon reconstructed from MRI and 3-DUS data was assessed using Jaccard index, Hausdorff distance and root mean square error (RMSE). The Jaccard index, Hausdorff distance and RMSE values were 0.76 ± 0.05, 2.70 ± 0.70 and 0.61 ± 0.10 mm, respectively. The level of agreement between MRI and 3-DUS for free Achilles tendon volume, length and average cross-sectional area (CSA) was assessed using Bland-Altman analysis. Compared to MRI, freehand 3-DUS overestimated volume, length and average CSA by 30.6 ± 15.8 mm3 (1.1% ± 0.6%), 0.3 ± 0.7 mm (0.6% ± 1.9%) and 0.3 ± 1.42 mm2 (0.4% ± 2.0%), respectively. The upper and lower limits of agreement between MRI and 3-DUS for volume, length and average CSA were -0.4 to 61.7 mm3 (-0.2% to 2.3%), -1.0 to 1.5 mm (-3.2% to 4.5%) and -2.5 to 3.1 mm2 (-3.5% to 4.3%), respectively. There were no significant differences between imaging methods in CSA along the length of the tendon. In conclusion, MRI and freehand 3-DUS may be considered equivalent methods for estimating shape and 3-D geometry of the free Achilles tendon. These findings, together with the practical benefits of being able to assess 3-D Achilles tendon shape and geometry in a laboratory environment and under isometric loading, make 3-DUS an attractive alternative to MRI for assessing 3-D free Achilles tendon macro-structure in future studies.

Is conservation of center of mass mechanics a priority in human walking? Insights from leg-length asymmetry experiments.

Center of mass (COM) control has been proposed to serve economy- and stability-related locomotor task objectives. However, given the lack of evidence supporting direct sensing and/or regulation of the COM, it remains unclear whether COM mechanics are prioritized in the control scheme of walking. We posit that peripheral musculoskeletal structures, e.g. muscle, are more realistic control targets than the COM, given their abundance of sensorimotor receptors and ability to influence whole-body energetics. As a first test of this hypothesis, we examined whether conservation of stance-phase joint mechanics is prioritized over COM mechanics in a locomotor task where simultaneous conservation of COM and joint mechanics is not feasible: imposed leg-length asymmetry. Positive joint mechanical cost of transport (work per distance traveled; COTJNT) was maintained at values closer to normal walking than COM mechanical cost of transport (COTCOM; P<0.05, N=15). Furthermore, compared with our measures of COM mechanics (COTCOM, COM displacement), joint-level variables (COTJNT, integrated total support moment) also displayed stronger conservation (less change from normal walking) when the participants' self-selected gait was assessed against other possible gait solutions. We conclude that when walking humans are exposed to an asymmetric leg-length perturbation, control of joint mechanics is prioritized over COM mechanics. Our results suggest that mechanical and metabolic effort is likely regulated via control of peripheral structures and not directly at the level of the COM. Joint mechanics may provide a more accurate representation of the underlying locomotor control targets and may prove advantageous in informing predictive models of human walking.

The influence of digital filter type, amplitude normalisation method, and co-contraction algorithm on clinically relevant surface electromyography data during clinical movement assessments.

There is a large and growing body of surface electromyography (sEMG) research using laboratory-specific signal processing procedures (i.e., digital filter type and amplitude normalisation protocols) and data analyses methods (i.e., co-contraction algorithms) to acquire practically meaningful information from these data. As a result, the ability to compare sEMG results between studies is, and continues to be challenging. The aim of this study was to determine if digital filter type, amplitude normalisation method, and co-contraction algorithm could influence the practical or clinical interpretation of processed sEMG data. Sixteen elite female athletes were recruited. During data collection, sEMG data was recorded from nine lower limb muscles while completing a series of calibration and clinical movement assessment trials (running and sidestepping). Three analyses were conducted: (1) signal processing with two different digital filter types (Butterworth or critically damped), (2) three amplitude normalisation methods, and (3) three co-contraction ratio algorithms. Results showed the choice of digital filter did not influence the clinical interpretation of sEMG; however, choice of amplitude normalisation method and co-contraction algorithm did influence the clinical interpretation of the running and sidestepping task. Care is recommended when choosing amplitude normalisation method and co-contraction algorithms if researchers/clinicians are interested in comparing sEMG data between studies.