Reliability of a human pose tracking algorithm for measuring upper limb joints: comparison with photography-based goniometry

Multimodal analysis of mother-child interaction using hyperscanning and diffusion maps

The current work aims to reveal mother-child synchronization patterns using several interaction modalities and combining them using the diffusion maps method. Twenty-two Hebrew-speaking toddlers (ages = 33 ± 5.38 months, 17 males) and their mothers (ages = 35 ± 5.79 years) participated in two interaction conditions while data was collected from several modalities, i.e. EEG, joint attention (measured through video coding of looking behavior), and motion analysis. Dimension reduction and data fusion of these modalities were performed using diffusion maps to enable a comprehensive assessment of mother-child synchronization dynamics. This multimodal approach allows better characterization of mother-child interaction and examining the associations between interaction patterns and maternal parenting style and their importance to the child's long-term language abilities.

Reliability and Validity Examination of a New Gait Motion Analysis System

Recent advancements have made two-dimensional (2D) clinical gait analysis systems more accessible and portable than traditional three-dimensional (3D) clinical systems. This study evaluates the reliability and validity of gait measurements using monocular and composite camera setups with VisionPose, comparing them to the Vicon 3D motion capture system as a reference. Key gait parameters-including hip and knee joint angles, and time and distance factors-were assessed under normal, maximum speed, and tandem gait conditions during level walking. The results show that the intraclass correlation coefficient (ICC(1,k)) for the 2D model exceeded 0.969 for the monocular camera and 0.963 for the composite camera for gait parameters. Time-distance gait parameters demonstrated excellent relative agreement across walking styles, while joint range of motion showed overall strong agreement. However, accuracy was lower for measurements during tandem walking. The Cronbach's alpha coefficient for time-distance parameters ranged from 0.932 to 0.999 (monocular) and from 0.823 to 0.998 (composite). In contrast, for joint range of motion, the coefficient varied more widely, ranging from 0.826 to 0.985 (monocular) and from 0.314 to 0.974 (composite). The correlation coefficients for spatiotemporal gait parameters were greater than 0.933 (monocular) and 0.837 (composite). However, for joint angle parameters, the coefficients were lower during tandem walking. This study underscores the potential of 2D models in clinical applications and highlights areas for improvement to enhance their reliability and application scope.

The Future of Clinical Active Shoulder Range of Motion Assessment, Best Practice, and Its Challenges: Narrative Review

Optimising outcomes after shoulder interventions requires objective shoulder range of motion (ROM) assessments. This narrative review examines video-based pose technologies and markerless motion capture, focusing on their clinical application for shoulder ROM assessment. Camera pose-based methods offer objective ROM measurements, though the accuracy varies due to the differences in gold standards, anatomical definitions, and deep learning techniques. Despite some biases, the studies report a high consistency, emphasising that methods should not be used interchangeably if they do not agree with each other. Smartphone cameras perform well in capturing 2D planar movements but struggle with that of rotational movements and forward flexion, particularly when thoracic compensations are involved. Proper camera positioning, orientation, and distance are key, highlighting the importance of standardised protocols in mobile phone-based ROM evaluations. Although 3D motion capture, per the International Society of Biomechanics recommendations, remains the gold standard, advancements in LiDAR/depth sensing, smartphone cameras, and deep learning show promise for reliable ROM assessments in clinical settings.

Orthopedic surgeon level joint angle assessment with artificial intelligence based on photography: a pilot study

Accurate assessment of shoulder range of motion (ROM) is crucial for evaluating patient progress. Traditional manual goniometry often lacks precision and is subject to inter-observer variability, especially in measuring shoulder internal rotation (IR). This study introduces an artificial intelligence (AI)-based approach that uses clinical photography to improve the accuracy of ROM quantification. We analyzed a total of 150 clinical photographs, including 100 shoulder and 50 elbow images, taken between January and April 2022. An MMPose model with an HR-NET backbone architecture, pre-trained on the COCO-WholeBody dataset, was used to detect 17 anatomical landmarks. A random forest classifier (PoseRF) then categorized poses, and ROM angles were calculated. Concurrently, two clinicians independently measured shoulder IR at the vertebral level, and inter-observer agreement was evaluated. Linear regression analyses were conducted to correlate the AI-derived measurements with the clinicians' assessments. The AI-based algorithm accurately detected anatomical landmarks in 96% of shoulder and 100% of elbow images. Pose detection achieved 95% accuracy overall, with 100% accuracy for specific shoulder (abduction, flexion, external rotation) and elbow (flexion, extension) poses. Intraclass correlation coefficients (ICCs) between the AI algorithm and human observers ranged from 0.965 to 0.997, indicating excellent inter-observer reliability. Kruskal-Wallis test showed no statistically significant differences in ROM measurements among the AI algorithm and two human observers across all joint angles (p > 0.05). The AI-based algorithm demonstrated performance comparable to that of human observers in quantifying shoulder and elbow ROM from clinical photographs. For shoulder internal rotation, the AI approach showed potential for improved consistency compared to traditional methods.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-024-00432-w.

Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion

Human Pose Estimation (HPE) is a computer vision application that utilizes deep learning techniques to precisely locate Key Joint Points (KJPs), enabling the accurate description of a person's pose. HPE models can be extended to facilitate Range of Motion (ROM) assessment by leveraging patient photographs. This study aims to evaluate and compare the performance of HPE models for assessing upper limbs ROM. A physiotherapist evaluated the degrees of ROM in shoulders (flexion, extension, and abduction) and elbows (flexion and extension) for fifty-two participants using both Universal Goniometer (UG) and five HPE models. Participants were instructed to repeat each movement three times to obtain measurements with the UG, then positioned while photos were captured using the NLMeasurer mobile application. The paired t-test, bias, and error measures were employed to evaluate the difference and agreement between measurement methods. Results indicated that the MoveNet Thunder INT16 model exhibited superior performance. Root Mean Square Errors obtained through this model were <10° in 8 of 10 analyzed movements. HPE models demonstrated better performance in shoulder flexion and abduction movements while exhibiting unsatisfactory performance in elbow flexion. Challenges such as image perspective distortion, environmental lighting conditions, images in monocular view, and complications in the pose may influence the models' performance. Nevertheless, HPE models show promise in identifying KJPs and facilitating ROM measurements, potentially enhancing convenience and efficiency in assessments. However, their current accuracy for this application is unsatisfactory, highlighting the need for caution when considering automated upper limb ROM measurement with them. The implementation of these models in clinical practice does not diminish the crucial role of examiners in carefully inspecting images and making adjustments to ensure measurement reliability.

Validity and Reliability of OpenPose-Based Motion Analysis in Measuring Knee Valgus during Drop Vertical Jump Test

OpenPose-based motion analysis (OpenPose-MA), utilizing deep learning methods, has emerged as a compelling technique for estimating human motion. It addresses the drawbacks associated with conventional three-dimensional motion analysis (3D-MA) and human visual detection-based motion analysis (Human-MA), including costly equipment, time-consuming analysis, and restricted experimental settings. This study aims to assess the precision of OpenPose-MA in comparison to Human-MA, using 3D-MA as the reference standard. The study involved a cohort of 21 young and healthy adults. OpenPose-MA employed the OpenPose algorithm, a deep learning-based open-source two-dimensional (2D) pose estimation method. Human-MA was conducted by a skilled physiotherapist. The knee valgus angle during a drop vertical jump task was computed by OpenPose-MA and Human-MA using the same frontal-plane video image, with 3D-MA serving as the reference standard. Various metrics were utilized to assess the reproducibility, accuracy and similarity of the knee valgus angle between the different methods, including the intraclass correlation coefficient (ICC) (1, 3), mean absolute error (MAE), coefficient of multiple correlation (CMC) for waveform pattern similarity, and Pearson's correlation coefficients (OpenPose-MA vs. 3D-MA, Human-MA vs. 3D-MA). Unpaired t-tests were conducted to compare MAEs and CMCs between OpenPose-MA and Human-MA. The ICCs (1,3) for OpenPose-MA, Human-MA, and 3D-MA demonstrated excellent reproducibility in the DVJ trial. No significant difference between OpenPose-MA and Human-MA was observed in terms of the MAEs (OpenPose: 2.4° [95%CI: 1.9-3.0°], Human: 3.2° [95%CI: 2.1-4.4°]) or CMCs (OpenPose: 0.83 [range: 0.99-0.53], Human: 0.87 [range: 0.24-0.98]) of knee valgus angles. The Pearson's correlation coefficients of OpenPose-MA and Human-MA relative to that of 3D-MA were 0.97 and 0.98, respectively. This study demonstrated that OpenPose-MA achieved satisfactory reproducibility, accuracy and exhibited waveform similarity comparable to 3D-MA, similar to Human-MA. Both OpenPose-MA and Human-MA showed a strong correlation with 3D-MA in terms of knee valgus angle excursion.

Estimation of Vertical Ground Reaction Force during Single-leg Landing Using Two-dimensional Video Images and Pose Estimation Artificial Intelligence

OBJECTIVE

Assessment of the vertical ground reaction force (VGRF) during landing tasks is crucial for physical therapy in sports. The purpose of this study was to determine whether the VGRF during a single-leg landing can be estimated from a two-dimensional (2D) video image and pose estimation artificial intelligence (AI).

METHODS

Eighteen healthy male participants (age: 23.0 ± 1.6 years) performed a single-leg landing task from a 30-cm height. The VGRF was measured using a force plate and estimated using center of mass (COM) position data from a 2D video image with pose estimation AI (2D-AI) and three-dimensional optical motion capture (3D-Mocap). The measured and estimated peak VGRFs were compared using a paired t-test and Pearson's correlation coefficient. The absolute errors of the peak VGRF were also compared between the two estimations.

RESULTS

No significant difference in the peak VGRF was found between the force plate measured VGRF and the 2D-AI or 3D-Mocap estimated VGRF (force plate: 3.37 ± 0.42 body weight [BW], 2D-AI: 3.32 ± 0.42 BW, 3D-Mocap: 3.50 ± 0.42 BW). There was no significant difference in the absolute error of the peak VGRF between the 2D-AI and 3D-Mocap estimations (2D-AI: 0.20 ± 0.16 BW, 3D-Mocap: 0.13 ± 0.09 BW, P = 0.163). The measured peak VGRF was significantly correlated with the estimated peak by 2D-AI (R = 0.835, P <0.001).

CONCLUSION

The results of this study indicate that peak VGRF estimation using 2D video images and pose estimation AI is useful for the clinical assessment of single-leg landing.

Automated, Vision-Based Goniometry and Range of Motion Calculation in Individuals With Suspected Ehlers-Danlos Syndromes/Generalized Hypermobility Spectrum Disorders: A Comparison of Pose-Estimation Libraries to Goniometric Measurements

Generalized joint hypermobility (GJH) often leads clinicians to suspect a diagnosis of Ehlers Danlos Syndrome (EDS), but it can be difficult to objectively assess. Video-based goniometry has been proposed to objectively estimate joint range of motion in hyperextended joints. As part of an exam of joint hypermobility at a specialized EDS clinic, a mobile phone was used to record short videos of 97 adults (89 female, 35.0 ± 9.9 years old) undergoing assessment of the elbows, knees, shoulders, ankles, and fifth fingers. Five body keypoint pose-estimation libraries (AlphaPose, Detectron, MediaPipe-Body, MoveNet - Thunder, OpenPose) and two hand keypoint pose-estimation libraries (AlphaPose, MediaPipe-Hands) were used to geometrically calculate the maximum angle of hyperextension or hyperflexion of each joint. A custom domain-specific model with a MobileNet-v2 backbone finetuned on data collected as part of this study was also evaluated for the fifth finger movement. Spearman's correlation was used to analyze the angles calculated from the tracked joint positions, the angles calculated from manually annotated keypoints, and the angles measured using a goniometer. Moderate correlations between the angles estimated using pose-tracked keypoints and the goniometer measurements were identified for the elbow (rho =.722; Detectron), knee (rho =.608; MoveNet - Thunder), shoulder (rho =.632; MoveNet - Thunder), and fifth finger (rho =.786; custom model) movements. The angles estimated from keypoints predicted by open-source libraries at the ankles were not significantly correlated with the goniometer measurements. Manually annotated angles at the elbows, knees, shoulders, and fifth fingers were moderately to strongly correlated to goniometer measurements but were weakly correlated for the ankles. There was not one pose-estimation library which performed best across all joints, so the library of choice must be selected separately for each joint of interest. This work evaluates several pose-estimation models as part of a vision-based system for estimating joint angles in individuals with suspected joint hypermobility. Future applications of the proposed system could facilitate objective assessment and screening of individuals referred to specialized EDS clinics.

The reliability and validity of joint range of motion measurement using zoom and a smartphone application

[Purpose] This study aimed to evaluate the reliability and validity of measuring the range of motion of joints using a remote videoconferencing system (Zoom) and a smartphone application. [Participants and Methods] This study included 16 young and healthy adults. The participants were instructed to perform shoulder joint flexion exercises in a seated position, with automatic motions, and maintain that posture throughout the measurement. Two measurements were performed: 1) angle measurement using a three-dimensional (3D) motion analyzer, and 2) angle measurement using the videoconference software, Zoom, and a smartphone application. Intra- and inter-rater reliabilities were calculated using the intraclass correlation coefficients (ICC). The degree of agreement between the representative values of each measurer and the 3D motion analyzer was examined. [Results] ICC (1, 1) for intra-examiner reliability were 0.912 and 0.996. For the inter-rater reliability, the ICC (2, 1) was 0.945. The correlation coefficient between each examiner's value and the value of the 3D motion analyzer was 0.955 and 0.980, respectively. The Bland-Altman analysis results indicated no systematic error. [Conclusion] The method of remotely measuring joint range of motion using Zoom and a smartphone application demonstrated high reliability and validity.

Digital health in musculoskeletal care: where are we heading?

BMC Musculoskeletal Disorders launched a Collection on digital health to get a sense of where the wind is blowing, and what impact these technologies are and will have on musculoskeletal medicine. This editorial summarizes findings and focuses on some key topics, which are valuable as digital health establishes itself in patient care. Elements discussed are digital tools for the diagnosis, prognosis and evaluation of rheumatic and musculoskeletal diseases, coupled together with advances in methodologies to analyse health records and imaging. Moreover, the acceptability and validity of these digital advances is discussed. In sum, this editorial and the papers presented in this article collection on Digital health in musculoskeletal care will give the interested reader both a glance towards which future we are heading, and which new challenges these advances bring.