Applications and limitations of current markerless motion capture methods for clinical gait biomechanics

The Effects of Load, Crank Position, and Sex on the Biomechanics and Performance during an Upper Body Wingate Anaerobic Test

INTRODUCTION

The upper body Wingate Anaerobic Test (WAnT) is a 30-s maximal effort sprint against a set load (percentage of body mass). However, there is no consensus on the optimal load and no differential values for males and females, even when there are well-studied anatomical and physiological differences in muscle mass for the upper body. Our goal was to describe the effects of load, sex, and crank position on the kinetics, kinematics, and performance of the upper body WAnT.

METHODS

Eighteen participants (9 females) performed three WAnTs at 3%, 4%, and 5% of body mass. Arm crank forces, 2D kinematics, and performance variables were recorded during each WAnT.

RESULTS

Our results showed an increase of ~49% effective force, ~36% peak power, ~5° neck flexion, and ~30° shoulder flexion from 3% to 5% load ( P < 0.05). Mean power and anaerobic capacity decreased by 15%, with no changes in fatigue index ( P < 0.05). The positions of higher force efficiency were at 12 and 6 o'clock. The least force efficiency occurred at 3 o'clock ( P < 0.05). Sex differences showed that males produced 97% more effective force and 109% greater mean power than females, with 11.7% more force efficiency ( P < 0.001). Males had 16° more head/neck flexion than females, and females had greater elbow joint variability with 17° more wrist extension at higher loads. Males cycled ~32% faster at 3% versus 5% WAnT load with a 65% higher angular velocity than females. Grip strength, maximal voluntary isometric contraction, mass, and height positively correlated with peak and mean power ( P < 0.001).

CONCLUSIONS

In conclusion, load, sex, and crank position have a significant impact on performance of the WAnT. These factors should be considered when developing and implementing an upper body WAnT.

Video-Based Kinematic Analysis of Movement Quality in a Phase 3 Clinical Trial of Troriluzole in Adults with Spinocerebellar Ataxia: A Post Hoc Analysis

INTRODUCTION

Traditional methods for assessing movement quality rely on subjective standardized scales and clinical expertise. This limitation creates challenges for assessing patients with spinocerebellar ataxia (SCA), in whom changes in mobility can be subtle and varied. We hypothesized that a machine learning analytic system might complement traditional clinician-rated measures of gait. Our objective was to use a video-based assessment of gait dispersion to compare the effects of troriluzole with placebo on gait quality in adults with SCA.

METHODS

Participants with SCA underwent gait assessment in a phase 3, double-blind, placebo-controlled trial of troriluzole (NCT03701399). Videos were processed through a deep learning pose extraction algorithm, followed by the estimation of a novel gait stability measure, the Pose Dispersion Index, quantifying the frame-by-frame symmetry, balance, and stability during natural and tandem walk tasks. The effects of troriluzole treatment were assessed in mixed linear models, participant-level grouping, and treatment group-by-visit week interaction adjusted for age, sex, baseline modified Functional Scale for the Assessment and Rating of Ataxia (f-SARA), and time since diagnosis.

RESULTS

From 218 randomized participants, 67 and 56 participants had interpretable videos of a tandem and natural walk attempt, respectively. At Week 48, individuals assigned to troriluzole exhibited significant (p = 0.010) improvement in tandem walk Pose Dispersion Index versus placebo {adjusted interaction coefficient: 0.584 [95% confidence interval (CI) 0.137 to 1.031]}. A similar, nonsignificant trend was observed in the natural walk assessment [coefficient: 1.198 (95% CI - 1.067 to 3.462)]. Further, lower baseline Pose Dispersion Index during the natural walk was significantly (p = 0.041) associated with a higher risk of subsequent falls [adjusted Poisson coefficient: - 0.356 [95% CI - 0.697 to - 0.014)].

CONCLUSION

Using this novel approach, troriluzole-treated subjects demonstrated improvement in gait as compared to placebo for the tandem walk. Machine learning applied to video-captured gait parameters can complement clinician-reported motor assessment in adults with SCA. The Pose Dispersion Index may enhance assessment in future research. TRIAL REGISTRATION-CLINICALTRIALS.

GOV IDENTIFIER

NCT03701399.

Marker Data Enhancement For Markerless Motion Capture

Objective

Human pose estimation models can measure movement from videos at a large scale and low cost; however, open-source pose estimation models typically detect only sparse keypoints, which leads to inaccurate joint kinematics. OpenCap, a freely available service for researchers to measure movement from videos, addresses this issue using a deep learning model- the marker enhancer-that transforms sparse keypoints into dense anatomical markers. However, OpenCap performs poorly on movements not included in the training data. Here, we create a much larger and more diverse training dataset and develop a more accurate and generalizable marker enhancer.

Methods

We compiled marker-based motion capture data from 1176 subjects and synthesized 1433 hours of keypoints and anatomical markers to train the marker enhancer. We evaluated its accuracy in computing kinematics using both benchmark movement videos and synthetic data representing unseen, diverse movements.

Results

The marker enhancer improved kinematic accuracy on benchmark movements (mean error: 4.1°, max: 8.7°) compared to using video keypoints (mean: 9.6°, max: 43.1°) and OpenCap's original enhancer (mean: 5.3°, max: 11.5°). It also better generalized to unseen, diverse movements (mean: 4.1°, max: 6.7°) than OpenCap's original enhancer (mean: 40.4°, max: 252.0°).

Conclusion

Our marker enhancer demonstrates both accuracy and generalizability across diverse movements.

Significance

We integrated the marker enhancer into OpenCap, thereby offering its thousands of users more accurate measurements across a broader range of movements.

Automating Video-Based Two-Dimensional Motion Analysis in Sport? Implications for Gait Event Detection, Pose Estimation, and Performance Parameter Analysis

BACKGROUND

Two-dimensional (2D) video is a common tool used during sports training and competition to analyze movement. In these videos, biomechanists determine key events, annotate joint centers, and calculate spatial, temporal, and kinematic parameters to provide performance reports to coaches and athletes. Automatic tools relying on computer vision and artificial intelligence methods hold promise to reduce the need for time-consuming manual methods.

OBJECTIVE

This study systematically analyzed the steps required to automate the video analysis workflow by investigating the applicability of a threshold-based event detection algorithm developed for 3D marker trajectories to 2D video data at four sampling rates; the agreement of 2D keypoints estimated by an off-the-shelf pose estimation model compared with gold-standard 3D marker trajectories projected to camera's field of view; and the influence of an offset in event detection on contact time and the sagittal knee joint angle at the key critical events of touch down and foot flat.

METHODS

Repeated measures limits of agreement were used to compare parameters determined by markerless and marker-based motion capture.

RESULTS

Results highlighted that a minimum video sampling rate of 100 Hz is required to detect key events, and the limited applicability of 3D marker trajectory-based event detection algorithms when using 2D video. Although detected keypoints showed good agreement with the gold-standard, misidentification of key events-such as touch down by 20 ms resulted in knee compression angle differences of up to 20°.

CONCLUSION

These findings emphasize the need for de novo accurate key event detection algorithms to automate 2D video analysis pipelines.

Differences between lower extremity joint running kinetics captured by marker-based and markerless systems were speed dependent

BACKGROUND

The development of computer vision technology has enabled the use of markerless movement tracking for biomechanical analysis. Recent research has reported the feasibility of markerless systems in motion analysis but has yet to fully explore their utility for capturing faster movements, such as running. Applied studies using markerless systems in clinical and sports settings are still lacking. Thus, the present study compared running biomechanics estimated by marker-based and markerless systems. Given running speed not only affects sports performance but is also associated with clinical injury prevention, diagnosis, and rehabilitation, we aimed to investigate the effects of speed on the comparison of estimated lower extremity joint moments and powers between markerless and marker-based technologies during treadmill running as a concurrent validating study.

METHODS

Kinematic data from marker-based/markerless technologies were collected, along with ground reaction force data, from 16 young adults running on an instrumented treadmill at 3 speeds: 2.24 m/s, 2.91 m/s, and 3.58 m/s (5.0 miles/h, 6.5 miles/h, and 8.0 miles/h). Sagittal plane moments and powers of the hip, knee, and ankle were calculated by inverse dynamic methods. Time series analysis and statistical parametric mapping were used to determine system differences.

RESULTS

Compared to the marker-based system, the markerless system estimated increased lower extremity joint kinetics with faster speed during the swing phase in most cases.

CONCLUSION

Despite the promising application of markerless technology in clinical settings, systematic markerless overestimation requires focused attention. Based on segment pose estimations, the centers of mass estimated by markerless technologies were farther away from the relevant distal joint centers, which led to greater joint moments and powers estimates by markerless vs. marker-based systems. The differences were amplified by running speed.

Emerging Innovations in Preoperative Planning and Motion Analysis in Orthopedic Surgery

In recent years, preoperative planning has undergone significant advancements, with a dual focus: improving the accuracy of implant placement and enhancing the prediction of functional outcomes. These breakthroughs have been made possible through the development of advanced processing methods for 3D preoperative images. These methods not only offer novel visualization techniques but can also be seamlessly integrated into computer-aided design models. Additionally, the refinement of motion capture systems has played a pivotal role in this progress. These "markerless" systems are more straightforward to implement and facilitate easier data analysis. Simultaneously, the emergence of machine learning algorithms, utilizing artificial intelligence, has enabled the amalgamation of anatomical and functional data, leading to highly personalized preoperative plans for patients. The shift in preoperative planning from 2D towards 3D, from static to dynamic, is closely linked to technological advances, which will be described in this instructional review. Finally, the concept of 4D planning, encompassing periarticular soft tissues, will be introduced as a forward-looking development in the field of orthopedic surgery.

Position paper on how technology for human motion analysis and relevant clinical applications have evolved over the past decades: Striking a balance between accuracy and convenience

BACKGROUND

Over the past decades, tremendous technological advances have emerged in human motion analysis (HMA).

RESEARCH QUESTION

How has technology for analysing human motion evolved over the past decades, and what clinical applications has it enabled?

METHODS

The literature on HMA has been extensively reviewed, focusing on three main approaches: Fully-Instrumented Gait Analysis (FGA), Wearable Sensor Analysis (WSA), and Deep-Learning Video Analysis (DVA), considering both technical and clinical aspects.

RESULTS

FGA techniques relying on data collected using stereophotogrammetric systems, force plates, and electromyographic sensors have been dramatically improved providing highly accurate estimates of the biomechanics of motion. WSA techniques have been developed with the advances in data collection at home and in community settings. DVA techniques have emerged through artificial intelligence, which has marked the last decade. Some authors have considered WSA and DVA techniques as alternatives to "traditional" HMA techniques. They have suggested that WSA and DVA techniques are destined to replace FGA.

SIGNIFICANCE

We argue that FGA, WSA, and DVA complement each other and hence should be accounted as "synergistic" in the context of modern HMA and its clinical applications. We point out that DVA techniques are especially attractive as screening techniques, WSA methods enable data collection in the home and community for extensive periods of time, and FGA does maintain superior accuracy and should be the preferred technique when a complete and highly accurate biomechanical data is required. Accordingly, we envision that future clinical applications of HMA would favour screening patients using DVA in the outpatient setting. If deemed clinically appropriate, then WSA would be used to collect data in the home and community to derive relevant information. If accurate kinetic data is needed, then patients should be referred to specialized centres where an FGA system is available, together with medical imaging and thorough clinical assessments.

The applicability of markerless motion capture for clinical gait analysis in children with cerebral palsy

The aim of this comparative, cross-sectional study was to determine whether markerless motion capture can track deviating gait patterns in children with cerebral palsy (CP) to a similar extent as marker-based motion capturing. Clinical gait analysis (CGA) was performed for 30 children with spastic CP and 15 typically developing (TD) children. Marker data were processed with the Human Body Model and video files with Theia3D markerless software, to calculate joint angles for both systems. Statistical parametric mapping paired t-tests were used to compare the trunk, pelvis, hip, knee and ankle joint angles, for both TD and CP, as well as for the deviation from the norm in the CP group. Individual differences were quantified using mean absolute differences. Markerless motion capture was able to track frontal plane angles and sagittal plane knee and ankle angles well, but individual deviations in pelvic tilt and transverse hip rotation as present in CP were not captured by the system. Markerless motion capture is a promising new method for CGA in children with CP, but requires improvement to better capture several clinically relevant deviations especially in pelvic tilt and transverse hip rotation.

Development of a Low-Cost Markerless Optical Motion Capture System for Gait Analysis and Anthropometric Parameter Quantification

Technological advancements have expanded the range of methods for capturing human body motion, including solutions involving inertial sensors (IMUs) and optical alternatives. However, the rising complexity and costs associated with commercial solutions have prompted the exploration of more cost-effective alternatives. This paper presents a markerless optical motion capture system using a RealSense depth camera and intelligent computer vision algorithms. It facilitates precise posture assessment, the real-time calculation of joint angles, and acquisition of subject-specific anthropometric data for gait analysis. The proposed system stands out for its simplicity and affordability in comparison to complex commercial solutions. The gathered data are stored in comma-separated value (CSV) files, simplifying subsequent analysis and data mining. Preliminary tests, conducted in controlled laboratory environments and employing a commercial MEMS-IMU system as a reference, revealed a maximum relative error of 7.6% in anthropometric measurements, with a maximum absolute error of 4.67 cm at average height. Stride length measurements showed a maximum relative error of 11.2%. Static joint angle tests had a maximum average error of 10.2%, while dynamic joint angle tests showed a maximum average error of 9.06%. The proposed optical system offers sufficient accuracy for potential application in areas such as rehabilitation, sports analysis, and entertainment.

The Use of Head-Mounted Display Systems for Upper Limb Kinematic Analysis in Post-Stroke Patients: A Perspective Review on Benefits, Challenges and Other Solutions

In recent years, there has been a notable increase in the clinical adoption of instrumental upper limb kinematic assessment. This trend aligns with the rising prevalence of cerebrovascular impairments, one of the most prevalent neurological disorders. Indeed, there is a growing need for more objective outcomes to facilitate tailored rehabilitation interventions following stroke. Emerging technologies, like head-mounted virtual reality (HMD-VR) platforms, have responded to this demand by integrating diverse tracking methodologies. Specifically, HMD-VR technology enables the comprehensive tracking of body posture, encompassing hand position and gesture, facilitated either through specific tracker placements or via integrated cameras coupled with sophisticated computer graphics algorithms embedded within the helmet. This review aims to present the state-of-the-art applications of HMD-VR platforms for kinematic analysis of the upper limb in post-stroke patients, comparing them with conventional tracking systems. Additionally, we address the potential benefits and challenges associated with these platforms. These systems might represent a promising avenue for safe, cost-effective, and portable objective motor assessment within the field of neurorehabilitation, although other systems, including robots, should be taken into consideration.

A Step Forward Understanding Directional Limitations in Markerless Smartphone-Based Gait Analysis: A Pilot Study

The progress in markerless technologies is providing clinicians with tools to shorten the time of assessment rapidly, but raises questions about the potential trade-off in accuracy compared to traditional marker-based systems. This study evaluated the OpenCap system against a traditional marker-based system-Vicon. Our focus was on its performance in capturing walking both toward and away from two iPhone cameras in the same setting, which allowed capturing the Timed Up and Go (TUG) test. The performance of the OpenCap system was compared to that of a standard marker-based system by comparing spatial-temporal and kinematic parameters in 10 participants. The study focused on identifying potential discrepancies in accuracy and comparing results using correlation analysis. Case examples further explored our results. The OpenCap system demonstrated good accuracy in spatial-temporal parameters but faced challenges in accurately capturing kinematic parameters, especially in the walking direction facing away from the cameras. Notably, the two walking directions observed significant differences in pelvic obliquity, hip abduction, and ankle flexion. Our findings suggest areas for improvement in markerless technologies, highlighting their potential in clinical settings.

Multimodal human motion dataset of 3D anatomical landmarks and pose keypoints

In this paper, we present a dataset that takes 2D and 3D human pose keypoints estimated from images and relates them to the location of 3D anatomical landmarks. The dataset contains 51,051 poses obtained from 71 persons in A-Pose while performing 7 movements (walking, running, squatting, and four types of jumping). These poses were scanned to build a collection of 3D moving textured meshes with anatomical correspondence. Each mesh in that collection was used to obtain the 3D locations of 53 anatomical landmarks, and 48 images were created using virtual cameras with different perspectives. 2D pose keypoints from those images were obtained using the MediaPipe Human Pose Landmarker, and their corresponding 3D keypoints were calculated by linear triangulation. The dataset consists of a folder for each participant containing two Track Row Column (TRC) files and one JSON file for each movement sequence. One TRC file is used to store the 3D data of the triangulated 3D keypoints while the other contains the 3D anatomical landmarks. The JSON file is used to store the 2D keypoints and the calibration parameters of the virtual cameras. The anthropometric characteristics of the participants are annotated in a single CSV file. These data are intended to be used in developments that require the transformation of existing human pose solutions in computer vision into biomechanical applications or simulations. This dataset can also be used in other applications related to training neural networks for human motion analysis and studying their influence on anthropometric characteristics.

Sensor-Based Quantification of MDS-UPDRS III Subitems in Parkinson's Disease Using Machine Learning

Wearable sensors could be beneficial for the continuous quantification of upper limb motor symptoms in people with Parkinson's disease (PD). This work evaluates the use of two inertial measurement units combined with supervised machine learning models to classify and predict a subset of MDS-UPDRS III subitems in PD. We attached the two compact wearable sensors on the dorsal part of each hand of 33 people with PD and 12 controls. Each participant performed six clinical movement tasks in parallel with an assessment of the MDS-UPDRS III. Random forest (RF) models were trained on the sensor data and motor scores. An overall accuracy of 94% was achieved in classifying the movement tasks. When employed for classifying the motor scores, the averaged area under the receiver operating characteristic values ranged from 68% to 92%. Motor scores were additionally predicted using an RF regression model. In a comparative analysis, trained support vector machine models outperformed the RF models for specific tasks. Furthermore, our results surpass the literature in certain cases. The methods developed in this work serve as a base for future studies, where home-based assessments of pharmacological effects on motor function could complement regular clinical assessments.

Gait pattern can alter aesthetic visual impression from a third-person perspective

Beauty is related to our lives in various ways and examining it from an interdisciplinary approach is essential. People are very concerned with their appearance. A widely accepted beauty ideal is that the thinner an individual is, the more beautiful they are. However, the effect of continuous motion on body form aesthetics is unclear. Additionally, an upright pelvic posture in the sagittal plane during walking seems to affect the aesthetic judgments of female appearance. We directly analyzed the influence of body form and walking pattern on aesthetic visual impressions from a third-person perspective with a two-way analysis of variance. Captured motion data for three conditions-upright pelvis, normal pelvis, and posteriorly tilted pelvic posture-were applied to each of three mannequins, representing thin, standard, and obese body forms. When participants watched stimulus videos of the mannequins walking with various postures, a significantly higher score for aesthetic visual impression was noted for an upright pelvic posture than for a posteriorly tilted pelvic posture, irrespective of body form (F(2, 119) = 79.89, p < 0.001, η2 = 0.54). These findings show that the third-person perspective of beauty can be improved even without being thin by walking with an upright pelvic posture.

Inter-trial variability is higher in 3D markerless compared to marker-based motion capture: Implications for data post-processing and analysis

Markerless motion capture has recently attracted significant interest in clinical gait analysis and human movement science. Its ease of use and potential to streamline motion capture recordings bear great potential for out-of-the-laboratory measurements in large cohorts. While previous studies have shown that markerless systems can achieve acceptable accuracy and reliability for kinematic parameters of gait, they also noted higher inter-trial variability of markerless data. Since increased inter-trial variability can have important implications for data post-processing and analysis, this study compared the inter-trial variability of simultaneously recorded markerless and marker-based data. For this purpose, the data of 18 healthy volunteers were used who were instructed to simulate four different gait patterns: physiological, crouch, circumduction, and equinus gait. Gait analysis was performed using the smartphone-based markerless system OpenCap and a marker-based motion capture system. We compared the inter-trial variability of both systems and also evaluated if changes in inter-trial variability may depend on the analyzed gait pattern. Compared to the marker-based data, we observed an increase of inter-trial variability for the markerless system ranging from 6.6% to 22.0% for the different gait patterns. Our findings demonstrate that the markerless pose estimation pipelines can introduce additionally variability in the kinematic data across different gait patterns and levels of natural variability. We recommend using averaged waveforms rather than single ones to mitigate this problem. Further, caution is advised when using variability-based metrics in gait and human movement analysis based on markerless data as increased inter-trial variability can lead to misleading results.

Markerless motion capture provides accurate predictions of ground reaction forces across a range of movement tasks

Measuring or estimating the forces acting on the human body during movement is critical for determining the biomechanical aspects relating to injury, disease and healthy ageing. In this study we examined whether quantifying whole-body motion (segmental accelerations) using a commercial markerless motion capture system could accurately predict three-dimensional ground reaction force during a diverse range of human movements: walking, running, jumping and cutting. We synchronously recorded 3D ground reaction forces (force instrumented treadmill or in-ground plates) with high-resolution video from eight cameras that were spatially calibrated relative to a common coordinate system. We used a commercially available software to reconstruct whole body motion, along with a geometric skeletal model to calculate the acceleration of each segment and hence the whole-body centre of mass and ground reaction force across each movement task. The average root mean square difference (RMSD) across all three dimensions and all tasks was 0.75 N/kg, with the maximum average RMSD being 1.85 N/kg for running vertical force (7.89 % of maximum). There was very strong agreement between peak forces across tasks, with R2 values indicating that the markerless prediction algorithm was able to predict approximately 95-99 % of the variance in peak force across all axes and movements. The results were comparable to previous reports using whole-body marker-based approaches and hence this provides strong proof-of-principle evidence that markerless motion capture can be used to predict ground reaction forces and therefore potentially assess movement kinetics with limited requirements for participant preparation.

Detection of kinematic abnormalities in persons with knee osteoarthritis using markerless motion capture during functional movement screen and daily activities

Background: The functional movement screen (FMS) has been used to identify deficiencies in neuromuscular capabilities and balance among athletes. However, its effectiveness in detecting movement anomalies within the population afflicted by knee osteoarthritis (KOA), particularly through the application of a family-oriented objective assessment technique, remains unexplored. The objective of this study is to investigate the sensitivity of the FMS and daily activities in identifying kinematic abnormalities in KOA people employing a markerless motion capture system. Methods: A total of 45 persons, presenting various Kellgren-Lawrence grades of KOA, along with 15 healthy controls, completed five tasks of the FMS (deep squat, hurdle step, and in-line lunge) and daily activities (walking and sit-to-stand), which were recorded using the markerless motion capture system. The kinematic waveforms and discrete parameters were subjected to comparative analysis. Results: Notably, the FMS exhibited greater sensitivity compared to daily activities, with knee flexion, trunk sagittal, and trunk frontal angles during in-line lunge emerging as the most responsive indicators. Conclusion: The knee flexion, trunk sagittal, and trunk frontal angles during in-line lunge assessed via the markerless motion capture technique hold promise as potential indicators for the objective assessment of KOA.

Digitalization in orthopaedics: a narrative review

Advances in technology and digital tools like the Internet of Things (IoT), artificial intelligence (AI), and sensors are shaping the field of orthopaedic surgery on all levels, from patient care to research and facilitation of logistic processes. Especially the COVID-19 pandemic, with the associated contact restrictions was an accelerator for the development and introduction of telemedical applications and digital alternatives to classical in-person patient care. Digital applications already used in orthopaedic surgery include telemedical support, online video consultations, monitoring of patients using wearables, smart devices, surgical navigation, robotic-assisted surgery, and applications of artificial intelligence in forms of medical image processing, three-dimensional (3D)-modelling, and simulations. In addition to that immersive technologies like virtual, augmented, and mixed reality are increasingly used in training but also rehabilitative and surgical settings. Digital advances can therefore increase the accessibility, efficiency and capabilities of orthopaedic services and facilitate more data-driven, personalized patient care, strengthening the self-responsibility of patients and supporting interdisciplinary healthcare providers to offer for the optimal care for their patients.

Advances in objective assessment of ergonomics in endoscopic surgery: a review

Background

Minimally invasive surgery, in particular endoscopic surgery, has revolutionized the benefits for patients, but poses greater challenges for surgeons in terms of ergonomics. Integrating ergonomic assessments and interventions into the multi-stage endoscopic procedure contributes to the surgeon's musculoskeletal health and the patient's intraoperative safety and postoperative recovery.

Objective

The purpose of this study was to overview the objective assessment techniques, tools and assessment settings involved in endoscopic procedures over the past decade and to identify the potential factors that induce differences in high workloads in endoscopic procedures and ultimately to design a framework for ergonomic assessment in endoscopic surgery.

Methods

Literature searches were systematically conducted in the OVID, pubmed and web of science database before October 2022, and studies evaluating ergonomics during the process of endoscopic procedures or simulated procedures were both recognized.

Results

Our systematic review of 56 studies underscores ergonomic variations in endoscopic surgery. While endoscopic procedures, predominantly laparoscopy, typically incur less physical load than open surgery, extended surgical durations notably elevate ergonomic risks. Surgeon characteristics, such as experience level and gender, significantly influence these risks, with less experienced and female surgeons facing greater challenges. Key assessment tools employed include electromyography for muscle fatigue and motion analysis for postural evaluation.

Conclusion

This review aims to provide a comprehensive analysis and framework of objective ergonomic assessments in endoscopic surgery, and suggesting avenues for future research and intervention strategies. By improving the ergonomic conditions for surgeons, we can enhance their overall health, mitigate the risk of WMSDs, and ultimately improve patient outcomes.

Augmented action observation: Theory and practical applications in sensorimotor rehabilitation

Sensory feedback is a fundamental aspect of effective motor learning in sport and clinical contexts. One way to provide this is through sensory augmentation, where extrinsic sensory information are associated with, and modulated by, movement. Traditionally, sensory augmentation has been used as an online strategy, where feedback is provided during physical execution of an action. In this article, we argue that action observation can be an additional effective channel to provide augmented feedback, which would be complementary to other, more traditional, motor learning and sensory augmentation strategies. Given these similarities between observing and executing an action, action observation could be used when physical training is difficult or not feasible, for example during immobilization or during the initial stages of a rehabilitation protocol when peripheral fatigue is a common issue. We review the benefits of observational learning and preliminary evidence for the effectiveness of using augmented action observation to improve learning. We also highlight current knowledge gaps which make the transition from laboratory to practical contexts difficult. Finally, we highlight the key areas of focus for future research.

Validity of AI-Based Gait Analysis for Simultaneous Measurement of Bilateral Lower Limb Kinematics Using a Single Video Camera

Accuracy validation of gait analysis using pose estimation with artificial intelligence (AI) remains inadequate, particularly in objective assessments of absolute error and similarity of waveform patterns. This study aimed to clarify objective measures for absolute error and waveform pattern similarity in gait analysis using pose estimation AI (OpenPose). Additionally, we investigated the feasibility of simultaneous measuring both lower limbs using a single camera from one side. We compared motion analysis data from pose estimation AI using video footage that was synchronized with a three-dimensional motion analysis device. The comparisons involved mean absolute error (MAE) and the coefficient of multiple correlation (CMC) to compare the waveform pattern similarity. The MAE ranged from 2.3 to 3.1° on the camera side and from 3.1 to 4.1° on the opposite side, with slightly higher accuracy on the camera side. Moreover, the CMC ranged from 0.936 to 0.994 on the camera side and from 0.890 to 0.988 on the opposite side, indicating a "very good to excellent" waveform similarity. Gait analysis using a single camera revealed that the precision on both sides was sufficiently robust for clinical evaluation, while measurement accuracy was slightly superior on the camera side.

How is Big Data reshaping preclinical aging research?

The exponential scientific and technological progress during the past 30 years has favored the comprehensive characterization of aging processes with their multivariate nature, leading to the advent of Big Data in preclinical aging research. Spanning from molecular omics to organism-level deep phenotyping, Big Data demands large computational resources for storage and analysis, as well as new analytical tools and conceptual frameworks to gain novel insights leading to discovery. Systems biology has emerged as a paradigm that utilizes Big Data to gain insightful information enabling a better understanding of living organisms, visualized as multilayered networks of interacting molecules, cells, tissues and organs at different spatiotemporal scales. In this framework, where aging, health and disease represent emergent states from an evolving dynamic complex system, context given by, for example, strain, sex and feeding times, becomes paramount for defining the biological trajectory of an organism. Using bioinformatics and artificial intelligence, the systems biology approach is leading to remarkable advances in our understanding of the underlying mechanism of aging biology and assisting in creative experimental study designs in animal models. Future in-depth knowledge acquisition will depend on the ability to fully integrate information from different spatiotemporal scales in organisms, which will probably require the adoption of theories and methods from the field of complex systems. Here we review state-of-the-art approaches in preclinical research, with a focus on rodent models, that are leading to conceptual and/or technical advances in leveraging Big Data to understand basic aging biology and its full translational potential.

AddBiomechanics: Automating model scaling, inverse kinematics, and inverse dynamics from human motion data through sequential optimization

Creating large-scale public datasets of human motion biomechanics could unlock data-driven breakthroughs in our understanding of human motion, neuromuscular diseases, and assistive devices. However, the manual effort currently required to process motion capture data and quantify the kinematics and dynamics of movement is costly and limits the collection and sharing of large-scale biomechanical datasets. We present a method, called AddBiomechanics, to automate and standardize the quantification of human movement dynamics from motion capture data. We use linear methods followed by a non-convex bilevel optimization to scale the body segments of a musculoskeletal model, register the locations of optical markers placed on an experimental subject to the markers on a musculoskeletal model, and compute body segment kinematics given trajectories of experimental markers during a motion. We then apply a linear method followed by another non-convex optimization to find body segment masses and fine tune kinematics to minimize residual forces given corresponding trajectories of ground reaction forces. The optimization approach requires approximately 3-5 minutes to determine a subject's skeleton dimensions and motion kinematics, and less than 30 minutes of computation to also determine dynamically consistent skeleton inertia properties and fine-tuned kinematics and kinetics, compared with about one day of manual work for a human expert. We used AddBiomechanics to automatically reconstruct joint angle and torque trajectories from previously published multi-activity datasets, achieving close correspondence to expert-calculated values, marker root-mean-square errors less than 2 cm, and residual force magnitudes smaller than 2% of peak external force. Finally, we confirmed that AddBiomechanics accurately reproduced joint kinematics and kinetics from synthetic walking data with low marker error and residual loads. We have published the algorithm as an open source cloud service at AddBiomechanics.org, which is available at no cost and asks that users agree to share processed and de-identified data with the community. As of this writing, hundreds of researchers have used the prototype tool to process and share about ten thousand motion files from about one thousand experimental subjects. Reducing the barriers to processing and sharing high-quality human motion biomechanics data will enable more people to use state-of-the-art biomechanical analysis, do so at lower cost, and share larger and more accurate datasets.

Validity and Reliability of POM-Checker for Measuring Shoulder Range of Motion in Healthy Participants: A Pilot Single-Center Comparative Study

BACKGROUND

The aim of this study was to compare shoulder movement measurements between a Kinect-based markerless ROM assessment device (POM-Checker) and a 3D motion capture analysis system (BTS SMART DX-400).

METHODS

This was a single-visit clinical trial designed to evaluate the validity and reliability of the POM-Checker. The primary outcome was to assess the equivalence between two measurement devices within the same set of participants, aiming to evaluate the validity of the POM-Checker compared to the gold standard device (3D Motion Analysis System). As this was a pilot study, six participants were included.

RESULTS

The intraclass correlation coefficient (ICC) and the corresponding 95% confidence intervals (CIs) were used to assess the reproducibility of the measurements. Among the 18 movements analyzed, 16 exhibited ICC values of >0.75, indicating excellent reproducibility.

CONCLUSION

The results showed that the POM-checker is reliable and validated to measure the range of motion of the shoulder joint.

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35-46% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6-1.6 ± 3.7-4.2˚) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (± 12˚) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.

Development of a Methodology for Low-Cost 3D Underwater Motion Capture: Application to the Biomechanics of Horse Swimming

Hydrotherapy has been utilized in horse rehabilitation programs for over four decades. However, a comprehensive description of the swimming cycle of horses is still lacking. One of the challenges in studying this motion is 3D underwater motion capture, which holds potential not only for understanding equine locomotion but also for enhancing human swimming performance. In this study, a marker-based system that combines underwater cameras and markers drawn on horses is developed. This system enables the reconstruction of the 3D motion of the front and hind limbs of six horses throughout an entire swimming cycle, with a total of twelve recordings. The procedures for pre- and post-processing the videos are described in detail, along with an assessment of the estimated error. This study estimates the reconstruction error on a checkerboard and computes an estimated error of less than 10 mm for segments of tens of centimeters and less than 1 degree for angles of tens of degrees. This study computes the 3D joint angles of the front limbs (shoulder, elbow, carpus, and front fetlock) and hind limbs (hip, stifle, tarsus, and hind fetlock) during a complete swimming cycle for the six horses. The ranges of motion observed are as follows: shoulder: 17 ± 3°; elbow: 76 ± 11°; carpus: 99 ± 10°; front fetlock: 68 ± 12°; hip: 39 ± 3°; stifle: 68 ± 7°; tarsus: 99 ± 6°; hind fetlock: 94 ± 8°. By comparing the joint angles during a swimming cycle to those observed during classical gaits, this study reveals a greater range of motion (ROM) for most joints during swimming, except for the front and hind fetlocks. This larger ROM is usually achieved through a larger maximal flexion angle (smaller minimal angle of the joints). Finally, the versatility of the system allows us to imagine applications outside the scope of horses, including other large animals and even humans.

Comparison of a single-view image-based system to a multi-camera marker-based system for human static pose estimation

The purpose of this study was to compare human static pose estimation data measured with a single-view image-based system and a multi-camera marker-based system. Thirty participants (20 male/10 female, mean ± standard deviation 29.1 ± 10.0 years old, 1.75 ± 0.10 m tall, 79.1 ± 18.0 kg) performed six repetitions each of static holds of arm-raises and squats, in a different orientation for each repetition. These trials were captured simultaneously with a 120-Hz 12-camera marker-based system and a variable-frequency single-view image-based system. Data for each trial were time-synchronized between the two systems using a near-infrared LED-light that was visible to both systems. Discrete measurements of bilateral shoulder angles during arm-raises and bilateral knee angles during squats were compared between the systems using Bland-Altman plots and descriptive statistics. Pearson correlation coefficients were calculated, comparing the participant trial mean values across systems. Finally, a two-way ANOVA was used to examine whether participant orientation in the capture volume significantly affected either system. Biases for discrete measurements ranged in magnitude from 1.3 to 1.9°, and standard deviations of the differences between systems ranged from 2.4 to 4.7°. Pearson correlation coefficients were all above 0.97, and the ANOVA was unable to find a statistically significant orientation effect for either system. Thus, the marker-based and image-based systems produced similar measurements of static shoulder and knee angles. Future work should examine more complex measurements using volumetric scan-based models and also investigate the ability of single-view image-based systems to measure dynamic movements.

Concurrent validity of smartphone-based markerless motion capturing to quantify lower-limb joint kinematics in healthy and pathological gait

Markerless motion capturing has the potential to provide a low-cost and accessible alternative to traditional marker-based systems for real-world biomechanical assessment. However, before these systems can be put into practice, we need to rigorously evaluate their accuracy in estimating joint kinematics for various gait patterns. This study evaluated the accuracy of a low-cost, open-source, and smartphone-based markerless motion capture system, namely OpenCap, for measuring 3D joint kinematics in healthy and pathological gait compared to a marker-based system. 21 healthy volunteers were instructed to walk with four different gait patterns: physiological, crouch, circumduction, and equinus gait. Three-dimensional kinematic data were simultaneously recorded using the markerless and a marker-based motion capture system. The root mean square error (RMSE) and the peak error were calculated between every joint kinematic variable obtained by both systems. We found an overall RMSE of 5.8 (SD: 1.8 degrees) and a peak error of 11.3 degrees (SD: 3.9). A repeated measures ANOVA with post hoc tests indicated significant differences in RMSE and peak errors between the four gait patterns (p ¡ 0.05). Physiological gait presented the lowest, crouch and circumduction gait the highest errors. Our findings indicate a roughly comparable accuracy to IMU-based approaches and commercial markerless multi-camera solutions. However, errors are still above clinically desirable thresholds of two to five degrees. While our findings highlight the potential of markerless systems for assessing gait kinematics, they also underpin the need to further improve the underlying deep learning algorithms to make markerless pose estimation a valuable tool in clinical settings.

Quantitative Comparison of Hand Kinematics Measured with a Markerless Commercial Head-Mounted Display and a Marker-Based Motion Capture System in Stroke Survivors

Upper-limb paresis is common after stroke. An important tool to assess motor recovery is to use marker-based motion capture systems to measure the kinematic characteristics of patients' movements in ecological scenarios. These systems are, however, very expensive and not readily available for many rehabilitation units. Here, we explored whether the markerless hand motion capabilities of the cost-effective Oculus Quest head-mounted display could be used to provide clinically meaningful measures. A total of 14 stroke patients executed ecologically relevant upper-limb tasks in an immersive virtual environment. During task execution, we recorded their hand movements simultaneously by means of the Oculus Quest's and a marker-based motion capture system. Our results showed that the markerless estimates of the hand position and peak velocity provided by the Oculus Quest were in very close agreement with those provided by a marker-based commercial system with their regression line having a slope close to 1 (maximum distance: mean slope = 0.94 ± 0.1; peak velocity: mean slope = 1.06 ± 0.12). Furthermore, the Oculus Quest had virtually the same sensitivity as that of a commercial system in distinguishing healthy from pathological kinematic measures. The Oculus Quest was as accurate as a commercial marker-based system in measuring clinically meaningful upper-limb kinematic parameters in stroke patients.

AddBiomechanics: Automating model scaling, inverse kinematics, and inverse dynamics from human motion data through sequential optimization

Creating large-scale public datasets of human motion biomechanics could unlock data-driven breakthroughs in our understanding of human motion, neuromuscular diseases, and assistive devices. However, the manual effort currently required to process motion capture data and quantify the kinematics and dynamics of movement is costly and limits the collection and sharing of large-scale biomechanical datasets. We present a method, called AddBiomechanics, to automate and standardize the quantification of human movement dynamics from motion capture data. We use linear methods followed by a non-convex bilevel optimization to scale the body segments of a musculoskeletal model, register the locations of optical markers placed on an experimental subject to the markers on a musculoskeletal model, and compute body segment kinematics given trajectories of experimental markers during a motion. We then apply a linear method followed by another non-convex optimization to find body segment masses and fine tune kinematics to minimize residual forces given corresponding trajectories of ground reaction forces. The optimization approach requires approximately 3-5 minutes to determine a subjecťs skeleton dimensions and motion kinematics, and less than 30 minutes of computation to also determine dynamically consistent skeleton inertia properties and fine-tuned kinematics and kinetics, compared with about one day of manual work for a human expert. We used AddBiomechanics to automatically reconstruct joint angle and torque trajectories from previously published multi-activity datasets, achieving close correspondence to expert-calculated values, marker root-mean-square errors less than 2 c m , and residual force magnitudes smaller than 2 % of peak external force. Finally, we confirmed that AddBiomechanics accurately reproduced joint kinematics and kinetics from synthetic walking data with low marker error and residual loads. We have published the algorithm as an open source cloud service at AddBiomechanics.org, which is available at no cost and asks that users agree to share processed and de-identified data with the community. As of this writing, hundreds of researchers have used the prototype tool to process and share about ten thousand motion files from about one thousand experimental subjects. Reducing the barriers to processing and sharing high-quality human motion biomechanics data will enable more people to use state-of-the-art biomechanical analysis, do so at lower cost, and share larger and more accurate datasets.

Gait analysis comparison between manual marking, 2D pose estimation algorithms, and 3D marker-based system

Introduction

Recent advances in Artificial Intelligence (AI) and Computer Vision (CV) have led to automated pose estimation algorithms using simple 2D videos. This has created the potential to perform kinematic measurements without the need for specialized, and often expensive, equipment. Even though there's a growing body of literature on the development and validation of such algorithms for practical use, they haven't been adopted by health professionals. As a result, manual video annotation tools remain pretty common. Part of the reason is that the pose estimation modules can be erratic, producing errors that are difficult to rectify. Because of that, health professionals prefer the use of tried and true methods despite the time and cost savings pose estimation can offer.

Methods

In this work, the gait cycle of a sample of the elderly population on a split-belt treadmill is examined. The Openpose (OP) and Mediapipe (MP) AI pose estimation algorithms are compared to joint kinematics from a marker-based 3D motion capture system (Vicon), as well as from a video annotation tool designed for biomechanics (Kinovea). Bland-Altman (B-A) graphs and Statistical Parametric Mapping (SPM) are used to identify regions of statistically significant difference.

Results

Results showed that pose estimation can achieve motion tracking comparable to marker-based systems but struggle to identify joints that exhibit small, but crucial motion.

Discussion

Joints such as the ankle, can suffer from misidentification of their anatomical landmarks. Manual tools don't have that problem, but the user will introduce a static offset across the measurements. It is proposed that an AI-powered video annotation tool that allows the user to correct errors would bring the benefits of pose estimation to professionals at a low cost.

Identifying modifiable risk factors and screening strategies associated with anterior cruciate ligament injury risk in children aged 6 to 13 years: A systematic review

Growing anterior cruciate ligament (ACL) injury incidence is reported in countries across Europe, North America and in Australia for 5-14-year-olds, yet research on injury risk reduction predominantly focuses on populations aged > 13 years. For injury risk reduction, it is crucial to understand (i) which modifiable risk factors are associated with ACL injury in children (6-13 years) and (ii) how these risk factors are assessed. Articles were grouped according to sex/gender and/or maturational/age differences and examined modifiable risk factors during different physical screening tasks. The included articles (n = 40) predominantly examined intrinsic risk factors in girls aged 10-13 years. Factors mechanically linked to increased ACL loading at this age included increased peak knee adductor moments, knee valgus angles, hip and knee extension, and ground reaction forces. Assessment focused on laboratory-based assessments (e.g., motion capture, force plates). This review concluded that modifiable risk factors are present in children aged 6-13 years and that injury risk reduction strategies should be implemented as early as possible regardless of sex/gender. Further, screening strategies need updating to be childhood specific and feasible for the wide community. Additional research on extrinsic risk factors, norm values and children aged 6-9 years could allow for more targeted risk reduction strategies.

Estimation of human spine orientation with inertial measurement units (IMU) at low sampling rate: How low can we go?

Studying people in their daily life is important for understanding conditions with multi-faceted aetiology such as chronic low back pain. Inertial measurement units can be used to reconstruct the posture and motion of the body outside of laboratories to enable this research. The battery life of these sensors strongly affects the usability of the system, since recharging them frequently is inconvenient and can lead to additional errors. A major determinant of the battery life for these sensors is sampling rate, but the relationship between sampling rate and accuracy in motion reconstruction is not well documented. We measured the spine of 12 participants using inertial measurement units across a variety of tasks such as sitting, standing, walking, and jogging. The orientation of the spine was reconstructed using several filters, including a novel filter developed specifically for high performance at low sampling frequencies. Benchmarking against optical motion capture, we developed a model showing that the error of all tested filters depends exponentially on the sampling frequency, with the optimal filter gains showing a similar exponential relationship. Using this model of error, we developed a criterion for recommending minimum sampling frequencies for accurate motion estimates for each task, finding frequencies ranging from about 13 to 35 Hz sufficient depending on the task. Although we only studied the spine, these models should provide insight into optimizing sampling rate and filter parameters for inertial measurements in general use.

Validation of Estimators for Weight-Bearing and Shoulder Joint Loads Using Instrumented Crutches

This research paper aimed to validate two methods for measuring loads during walking with instrumented crutches: one method to estimate partial weight-bearing on the lower limbs and another to estimate shoulder joint reactions. Currently, gait laboratories, instrumented with high-end measurement systems, are used to extract kinematic and kinetic data, but such facilities are expensive and not accessible to all patients. The proposed method uses instrumented crutches to measure ground reaction forces and does not require any motion capture devices or force platforms. The load on the lower limbs is estimated by subtracting the forces measured by the crutches from the subject's total weight. Since the model does not consider inertia contribution in dynamic conditions, the estimation improves with low walking cadence when walking with the two-point contralateral and the three-point partial weight-bearing patterns considered for the validation tests. The shoulder joint reactions are estimated using linear regression, providing accurate values for the forces but less accurate torque estimates. The crutches data are acquired and processed in real-time, allowing for immediate feedback, and the system can be used outdoors in real-world walking conditions. The validation of this method could lead to better monitoring of partial weight-bearing and shoulder joint reactions, which could improve patient outcomes and reduce complications.

Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT)

Distinguishing pathological gait is challenging in neurology because of the difficulty of capturing total body movement and its analysis. We aimed to obtain a convenient recording with an iPhone and establish an algorithm based on deep learning. From May 2021 to November 2022 at Yamagata University Hospital, Shiga University, and Takahata Town, patients with idiopathic normal pressure hydrocephalus (n = 48), Parkinson's disease (n = 21), and other neuromuscular diseases (n = 45) comprised the pathological gait group (n = 114), and the control group consisted of 160 healthy volunteers. iPhone application TDPT-GT captured the subjects walking in a circular path of about 1 meter in diameter, a markerless motion capture system, with an iPhone camera, which generated the three-axis 30 frames per second (fps) relative coordinates of 27 body points. A light gradient boosting machine (Light GBM) with stratified k-fold cross-validation (k = 5) was applied for gait collection for about 1 min per person. The median ability model tested 200 frames of each person's data for its distinction capability, which resulted in the area under a curve of 0.719. The pathological gait captured by the iPhone could be distinguished by artificial intelligence.

[Motion analysis systems in research and for practicing orthopedists]

BACKGROUND

Complex biomechanical motion analysis can provide relevant information for a variety of orthopedic problems. When purchasing motion analysis systems, in addition to the classical measurement quality criteria (validity, reliability, objectivity), spatial and temporal conditions, as well as the requirements for the qualification of the measuring personnel should be considered.

APPLICATION

In complex movement analysis, systems are used to determine kinematics, kinetics and muscle activity (electromyography). This article gives an overview of methods of complex biomechanical motion analysis for use in orthopaedic research or for individual patient care. In addition to the use for pure movement analysis, the use of movement analysis methods in the field of biofeedback training is discussed.

ACQUISITION

For the specific acquisition of motion analysis systems, it is recommended to contact professional societies (e.g., the German Society for Biomechanics),universities with existing motion analysis facilities or distributors in the field of biomechanics.

Comparison of kinematics between Theia markerless and conventional marker-based gait analysis in clinical patients

BACKGROUND

Markerless motion capture systems have the potential to make clinical gait analysis more efficient and convenient. Theia3D is a commercially available markerless system that may serve as an alternative to traditional gait analysis for clinical gait laboratories.

RESEARCH QUESTION

What is the concurrent validity of markerless gait analysis using Theia3D compared to traditional marker-based gait analysis in pediatric clinical gait patients?

METHODS

Thirty-six patients (20 male, age 2-25 years) with a range of diagnoses underwent clinical gait analysis with data being captured concurrently by a traditional marker-based motion capture system (Vicon Nexus) and a commercial markerless system (Theia3D). Multiple left strides were averaged for each subject, and the difference in kinematics (Theia - Vicon) was calculated over the gait cycle and evaluated using root mean square difference (RMSD), mean difference, and RMSD after subtracting the mean value across the gait cycle (RMSD_offset). Sub-analysis was performed for 25 patients with foot deformities, 9 wearing ankle-foot orthoses, and 6 walking with assistance (cane, crutches, walker, or handheld).

RESULTS

Kinematics showed similar patterns between the marker-based and markerless systems. RMSD was < 6° except for pelvic tilt, hip flexion, ankle inversion, foot progression, and transverse plane rotation of the hip, knee, and ankle. These measures mainly differed due to an offset between the curves. After adjusting for offsets, all RMSD_offset were < 6°. RMSD was larger for patients with foot deformities, wearing orthoses, or using assistive devices, but all RMSD_offset were still < 8°. In some cases, however, the markerless system had greater trial-to-trial variability, showed a larger knee varus "bump" in swing, or failed to track the subject.

SIGNIFICANCE

This study provides preliminary evidence of concurrent validity of Theia3D for pediatric patients with abnormal gait. However, some questions remain regarding identification of the knee axis and for patients with foot deformity or assistive devices.

Quantifying Jump Height Using Markerless Motion Capture with a Single Smartphone

Goal: The countermovement jump (CMJ) is commonly used to measure lower-body explosive power. This study evaluates how accurately markerless motion capture (MMC) with a single smartphone can measure bilateral and unilateral CMJ jump height. Methods: First, three repetitions each of bilateral and unilateral CMJ were performed by sixteen healthy adults (mean age: 30.87 [Formula: see text] 7.24 years; mean BMI: 23.14 [Formula: see text] 2.55 [Formula: see text]) on force plates and simultaneously captured using optical motion capture (OMC) and one smartphone camera. Next, MMC was performed on the smartphone videos using OpenPose. Then, we evaluated MMC in quantifying jump height using the force plate and OMC as ground truths. Results: MMC quantifies jump heights with ICC between 0.84 and 0.99 without manual segmentation and camera calibration. Conclusions: Our results suggest that using a single smartphone for markerless motion capture is promising.

Inter-Device Reliability of a Three-Dimensional Markerless Motion Capture System Quantifying Elementary Movement Patterns in Humans

With advancements in technology able to quantify wide-ranging features of human movement, the aim of the present study was to investigate the inter-device technological reliability of a three-dimensional markerless motion capture system (3D-MCS), quantifying different movement tasks. A total of 20 healthy individuals performed a test battery consisting of 29 different movements, from which 214 different metrics were derived. Two 3D-MCS located in close proximity were utilized to quantify movement characteristics. Independent sample t-tests with selected reliability statistics (i.e., intraclass correlation coefficient (ICC), effect sizes, and mean absolute differences) were used to evaluate the agreement between the two systems. The study results suggested that 95.7% of all metrics analyzed revealed negligible or small between-device effect sizes. Further, 91.6% of all metrics analyzed showed moderate or better agreement when looking at the ICC values, while 32.2% of all metrics showed excellent agreement. For metrics measuring joint angles (198 metrics), the mean difference between systems was 2.9 degrees, while for metrics investigating distance measures (16 metrics; e.g., center of mass depth), the mean difference between systems was 0.62 cm. Caution is advised when trying to generalize the study findings beyond the specific technology and software used in this investigation. Given the technological reliability reported in this study, as well as the logistical and time-related limitations associated with marker-based motion capture systems, it may be suggested that 3D-MCS present practitioners with an opportunity to reliably and efficiently measure the movement characteristics of patients and athletes. This has implications for monitoring the health/performance of a broad range of populations.

Level of Agreement between the MotionMetrix System and an Optoelectronic Motion Capture System for Walking and Running Gait Measurements

Markerless motion capture systems (MCS) have been developed as an alternative solution to overcome the limitations of 3D MCS as they provide a more practical and efficient setup process given, among other factors, the lack of sensors attached to the body. However, this might affect the accuracy of the measures recorded. Thus, this study is aimed at evaluating the level of agreement between a markerless MSC (i.e., MotionMetrix) and an optoelectronic MCS (i.e., Qualisys). For such purpose, 24 healthy young adults were assessed for walking (at 5 km/h) and running (at 10 and 15 km/h) in a single session. The parameters obtained from MotionMetrix and Qualisys were tested in terms of level of agreement. When walking at 5 km/h, the MotionMetrix system significantly underestimated the stance and swing phases, as well as the load and pre-swing phases (p < 0.05) reporting also relatively low systematic bias (i.e., ≤ -0.03 s) and standard error of the estimate (SEE) (i.e., ≤0.02 s). The level of agreement between measurements was perfect (r > 0.9) for step length left and cadence and very large (r > 0.7) for step time left, gait cycle, and stride length. Regarding running at 10 km/h, bias and SEE analysis revealed significant differences for most of the variables except for stride time, rate and length, swing knee flexion for both legs, and thigh flexion left. The level of agreement between measurements was very large (r > 0.7) for stride time and rate, stride length, and vertical displacement. At 15 km/h, bias and SEE revealed significant differences for vertical displacement, landing knee flexion for both legs, stance knee flexion left, thigh flexion, and extension for both legs. The level of agreement between measurements in running at 15 km/h was almost perfect (r > 0.9) when comparing Qualisys and MotionMetrix parameters for stride time and rate, and stride length. The agreement between the two motion capture systems varied for different variables and speeds of locomotion, with some variables demonstrating high agreement while others showed poor agreement. Nonetheless, the findings presented here suggest that the MotionMetrix system is a promising option for sports practitioners and clinicians interested in measuring gait variables, particularly in the contexts examined in the study.

A Beta Version of an Application Based on Computer Vision for the Assessment of Knee Valgus Angle: A Validity and Reliability Study

BACKGROUND

In handball, the kinematics of the frontal plane seem to be one of the most important factors for the development of lower limb injuries. The knee valgus angle is a fundamental axis for injury prevention and is usually measured with 2D systems such as Kinovea software (Version 0.9.4.). Technological advances such as computer vision have the potential to revolutionize sports medicine. However, the validity and reliability of computer vision must be evaluated before using it in clinical practice. The aim of this study was to analyze the test-retest and inter-rater reliability and the concurrent validity of a beta version app based on computer vision for the measurement of knee valgus angle in elite handball athletes.

METHODS

The knee valgus angle of 42 elite handball athletes was measured. A frontal photo during a single-leg squat was taken, and two examiners measured the angle by the beta application based on computer vision at baseline and at one-week follow-up to calculate the test-retest and inter-rater reliability. A third examiner assessed the knee valgus angle using 2D Kinovea software to calculate the concurrent validity.

RESULTS

The knee valgus angle in the elite handball athletes was 158.54 ± 5.22°. The test-retest reliability for both examiners was excellent, showing an Intraclass Correlation Coefficient (ICC) of 0.859-0.933. The inter-rater reliability showed a moderate ICC: 0.658 (0.354-0.819). The standard error of the measurement with the app was stated between 1.69° and 3.50°, and the minimum detectable change was stated between 4.68° and 9.70°. The concurrent validity was strong r = 0.931; p < 0.001.

CONCLUSIONS

The computer-based smartphone app showed an excellent test-retest and inter-rater reliability and a strong concurrent validity compared to Kinovea software for the measurement of the knee valgus angle.

Dynamic stability during level walking and obstacle crossing in children aged 2–5 years estimated by marker-less motion capture

In the present study, dynamic stability during level walking and obstacle crossing in typically developing children aged 2–5 years (n = 13) and healthy young adults (n = 19) was investigated. The participants were asked to walk along unobstructed and obstructed walkways. The height of the obstacle was set at 10% of the leg length. Gait motion was captured by three RGB cameras. 2D body landmarks were estimated using OpenPose, a marker-less motion capture algorithm, and converted to 3D using direct linear transformation (DLT). Dynamic stability was evaluated using the margin of stability (MoS) in the forward and lateral directions. All the participants successfully crossed the obstacles. Younger children crossed the obstacle more carefully to avoid falls, as evidenced by obviously decreased gait speed just before the obstacle in 2-year-olds and the increased in maximum toe height with younger age. There was no significant difference in the MoS at the instant of heel contact between children and adults during level walking and obstacle crossing in the forward direction, although children increased the step length of the lead leg to a greater extent than the adults to ensure base of support (BoS)-center of mass (CoM) distance. In the lateral direction, children exhibited a greater MoS than adults during level walking [children: 9.5%, adults: 6.5%, median, W = 39.000, p &lt; .001, rank-biserial correlation = −0.684]; however, some children exhibited a smaller MoS during obstacle crossing [lead leg: −5.9% to 3.6% (min–max) for 4 children, 4.7%–6.4% [95% confidence interval (CI)] for adults, p &lt; 0.05; trail leg: 0.1%–4.4% (min–max) for 4 children, 4.7%–6.4% (95% CI) for adults, p &lt; 0.05]]. These results indicate that in early childhood, locomotor adjustment needed to avoid contact with obstacles can be observed, whereas lateral dynamic stability is frangible.

Tracking motion kinematics and tremor with intrinsic oscillatory property of instrumental mechanics

Tracking kinematic details of motor behaviors is a foundation to study the neuronal mechanism and biology of motor control. However, most of the physiological motor behaviors and movement disorders, such as gait, balance, tremor, dystonia, and myoclonus, are highly dependent on the overall momentum of the whole-body movements. Therefore, tracking the targeted movement and overall momentum simultaneously is critical for motor control research, but it remains an unmet need. Here, we introduce the intrinsic oscillatory property (IOP), a fundamental mechanical principle of physics, as a method for motion tracking in a force plate. The overall kinetic energy of animal motions can be transformed into the oscillatory amplitudes at the designed IOP frequency of the force plate, while the target movement has its own frequency features and can be tracked simultaneously. Using action tremor as an example, we reported that force plate-based IOP approach has superior performance and reliability in detecting both tremor severity and tremor frequency, showing a lower level of coefficient of variation (CV) compared with video- and accelerometer-based motion tracking methods and their combination. Under the locomotor suppression effect of medications, therapeutic effects on tremor severity can still be quantified by dynamically adjusting the overall locomotor activity detected by IOP. We further validated IOP method in optogenetic-induced movements and natural movements, confirming that IOP can represent the intensity of general rhythmic and nonrhythmic movements, thus it can be generalized as a common approach to study kinematics.

Towards Single Camera Human 3D-Kinematics

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple de-coupled steps to estimate the kinematics of a person from videos. Most current techniques work in a multi-step approach by first detecting the pose of the body and then fitting a musculoskeletal model to the data for accurate kinematic estimation. Errors in training data of the pose detection algorithms, model scaling, as well the requirement of multiple cameras limit the use of these techniques in a clinical setting. Our goal is to pave the way toward fast, easily applicable and accurate 3D kinematic estimation. To this end, we propose a novel approach for direct 3D human kinematic estimation D3KE from videos using deep neural networks. Our experiments demonstrate that the proposed end-to-end training is robust and outperforms 2D and 3D markerless motion capture based kinematic estimation pipelines in terms of joint angles error by a large margin (35% from 5.44 to 3.54 degrees). We show that D3KE is superior to the multi-step approach and can run at video framerate speeds. This technology shows the potential for clinical analysis from mobile devices in the future.

Estimating Ground Reaction Forces from Two-Dimensional Pose Data: A Biomechanics-Based Comparison of AlphaPose, BlazePose, and OpenPose

The adoption of computer vision pose estimation approaches, used to identify keypoint locations which are intended to reflect the necessary anatomical landmarks relied upon by biomechanists for musculoskeletal modelling, has gained increasing traction in recent years. This uptake has been further accelerated by keypoint use as inputs into machine learning models used to estimate biomechanical parameters such as ground reaction forces (GRFs) in the absence of instrumentation required for direct measurement. This study first aimed to investigate the keypoint detection rate of three open-source pose estimation models (AlphaPose, BlazePose, and OpenPose) across varying movements, camera views, and trial lengths. Second, this study aimed to assess the suitability and interchangeability of keypoints detected by each pose estimation model when used as inputs into machine learning models for the estimation of GRFs. The keypoint detection rate of BlazePose was distinctly lower than that of AlphaPose and OpenPose. All pose estimation models achieved a high keypoint detection rate at the centre of an image frame and a lower detection rate in the true sagittal plane camera field of view, compared with slightly anteriorly or posteriorly located quasi-sagittal plane camera views. The three-dimensional ground reaction force, instantaneous loading rate, and peak force for running could be estimated using the keypoints of all three pose estimation models. However, only AlphaPose and OpenPose keypoints could be used interchangeably with a machine learning model trained to estimate GRFs based on AlphaPose keypoints resulting in a high estimation accuracy when OpenPose keypoints were used as inputs and vice versa. The findings of this study highlight the need for further evaluation of computer vision-based pose estimation models for application in biomechanical human modelling, and the limitations of machine learning-based GRF estimation models that rely on 2D keypoints. This is of particular relevance given that machine learning models informing athlete monitoring guidelines are being developed for application related to athlete well-being.

Comparison of Lower Extremity Joint Moment and Power Estimated by Markerless and Marker-Based Systems during Treadmill Running

Background: Markerless (ML) motion capture systems have recently become available for biomechanics applications. Evidence has indicated the potential feasibility of using an ML system to analyze lower extremity kinematics. However, no research has examined ML systems’ estimation of the lower extremity joint moments and powers. This study aimed to compare lower extremity joint moments and powers estimated by marker-based (MB) and ML motion capture systems. Methods: Sixteen volunteers ran on a treadmill for 120 s at 3.58 m/s. The kinematic data were simultaneously recorded by 8 infrared cameras and 8 high-resolution video cameras. The force data were recorded via an instrumented treadmill. Results: Greater peak magnitudes for hip extension and flexion moments, knee flexion moment, and ankle plantarflexion moment, along with their joint powers, were observed in the ML system compared to an MB system (p < 0.0001). For example, greater hip extension (MB: 1.42 ± 0.29 vs. ML: 2.27 ± 0.45) and knee flexion (MB: −0.74 vs. ML: −1.17 nm/kg) moments were observed in the late swing phase. Additionally, the ML system’s estimations resulted in significantly smaller peak magnitudes for knee extension moment, along with the knee production power (p < 0.0001). Conclusions: These observations indicate that inconsistent estimates of joint center position and segment center of mass between the two systems may cause differences in the lower extremity joint moments and powers. However, with the progression of pose estimation in the markerless system, future applications can be promising.

Feasibility and validity of a single camera CNN driven musculoskeletal model for muscle force estimation during upper extremity strength exercises: Proof-of-concept

Muscle force analysis can be essential for injury risk estimation and performance enhancement in sports like strength training. However, current methods to record muscle forces including electromyography or marker-based measurements combined with a musculoskeletal model are time-consuming and restrict the athlete's natural movement due to equipment attachment. Therefore, the feasibility and validity of a more applicable method, requiring only a single standard camera for the recordings, combined with a deep-learning model and musculoskeletal model is evaluated in the present study during upper-body strength exercises performed by five athletes. Comparison of muscle forces obtained by the single camera driven model against those obtained from a state-of-the art marker-based driven musculoskeletal model revealed strong to excellent correlations and reasonable RMSD's of 0.4–2.1% of the maximum force (Fmax) for prime movers, and weak to strong correlations with RMSD's of 0.4–0.7% Fmax for stabilizing and secondary muscles. In conclusion, a single camera deep-learning driven model is a feasible method for muscle force analysis in a strength training environment, and first validity results show reasonable accuracies, especially for prime mover muscle forces. However, it is evident that future research should investigate this method for a larger sample size and for multiple exercises.

Synthesising 2D Video from 3D Motion Data for Machine Learning Applications

To increase the utility of legacy, gold-standard, three-dimensional (3D) motion capture datasets for computer vision-based machine learning applications, this study proposed and validated a method to synthesise two-dimensional (2D) video image frames from historic 3D motion data. We applied the video-based human pose estimation model OpenPose to real (in situ) and synthesised 2D videos and compared anatomical landmark keypoint outputs, with trivial observed differences (2.11−3.49 mm). We further demonstrated the utility of the method in a downstream machine learning use-case in which we trained and then tested the validity of an artificial neural network (ANN) to estimate ground reaction forces (GRFs) using synthesised and real 2D videos. Training an ANN to estimate GRFs using eight OpenPose keypoints derived from synthesised 2D videos resulted in accurate waveform GRF estimations (r > 0.9; nRMSE < 14%). When compared with using the smaller number of real videos only, accuracy was improved by adding the synthetic views and enlarging the dataset. The results highlight the utility of the developed approach to enlarge small 2D video datasets, or to create 2D video images to accompany 3D motion capture datasets to make them accessible for machine learning applications.

Alzheimer's Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning

Alzheimer's disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort.