Estimation and validation of temporal gait features using a markerless 2D video system

Cross-Spatiotemporal Graph Convolution Networks for Skeleton-Based Parkinsonian Gait MDS-UPDRS Score Estimation

Gait impairment in Parkinson's Disease (PD) is quantitatively assessed using the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS), a well-established clinical tool. Objective and efficient PD gait assessment is crucial for developing interventions to slow or halt its advancement. Skeleton-based PD gait MDS-UPDRS score estimation has attracted increasing interest in improving diagnostic efficiency and objectivity. However, previous works ignore the important cross-spacetime dependencies between joints in PD gait. Moreover, existing PD gait skeleton datasets are very small, which is a big issue in deep learning-based gait studies. In this work, we collect a sizable PD gait skeleton dataset by multi-view Azure Kinect sensors. The collected dataset contains 102 PD patients and 30 healthy older adults. In addition, gait data from 16 young adults (aged 24-50 years) are collected to further examine the effect of age on PD gait assessment. For skeleton-based automatic PD gait analysis, we propose a novel cross-spatiotemporal graph convolution network (CST-GCN) to learn complex features of gait patterns. Specifically, a gait graph labeling strategy is designed to assemble and group cross-spacetime neighbors of the root node according to the spatiotemporal semantics of the gait skeleton. Based on this strategy, the CST-GCN module explicitly models the cross-spacetime dependencies among joints. Finally, a dual-path model is presented to realize the modeling and fusion of spatial, temporal, and cross-spacetime gait features. Extensive experiments validate the effectiveness of our method on the collected dataset.

Validity of assessing level walking with the 2D motion analysis software TEMPLO and reliability of 3D marker application

In gait analysis, knowledge on validity and reliability of instruments and influences caused by the examiner's performance is of crucial interest. These measurement properties are not yet known for commonly used, low-cost two-dimensional (2D) video-based systems. The purpose of this study was to assess the concurrent validity of a video-based 2D system against a three-dimensional (3D) reference standard, as well as the inter-rater reliability, and test-retest reliability of 3D marker application. Level walking was captured simultaneously by a 2D and a 3D system. Reflective markers were applied independently by three raters and repeated by one rater on a second day. We assessed the agreement between the two systems, as well as reproducibility, and inter-rater agreement of derived spatio-temporal parameters and sagittal kinematics. Nineteen healthy participants completed this study. 2D gait analysis provides a possibility to accurately assess parameters such as stride time, stride length, gait velocity, and knee RoM. Interrater and test-retest reliability of 3D gait analysis are generally acceptable, except for the parameters toe-off and pelvic RoM. This is the first study to publish measurement properties of a commercially available 2D video-based gait analysis system, which can support interpretation of gait pattern near the sagittal plane.

Is a greater degree of constraint really harmful? Clinical biomechanical comparative study between condylar constrained knee and rotating hinge prosthesis

BACKGROUND

The real degree of constraint of rotating hinge knee and condylar constrained prostheses is a matter of discussion in revision knee arthroplasty. The objective of this study is to compare the tibial rotation between implants in the clinical settings.

METHODS

An investigator blinded experimental study was designed including 20 patients: in 10 of them a rotating hinge knee prosthesis (Endomodel®, LINK) was implanted and in the remaining 10 a constrained condylar knee prosthesis (LCCK®, Zimmer) was used. A medial parapatellar approach was performed and implantation was performed according to conventional surgical technique. Tibial rotation was measured with two accelerometers in full extension and at 30°, 60° and 90° of flexion. Pre and postoperative Knee Injury and Osteoarthritis Outcome Score was recorded.

FINDINGS

Both groups were homogenous in age (73.4 years in rotating hinge knee prosthesis vs 74 years in constrained condylar knee group), sex, laterality and preoperative Knee Injury and Osteoarthritis Outcome Score (p > 0.05). The postoperative Knee Injury and Osteoarthritis Outcome Score was significantly higher in the rotating hinge knee prosthesis group (80.98 vs 76.28). The degrees of tibial rotation measured by inertial sensors in the rotating hinge knee prosthesis group were also significantly higher than those measured in the constrained condylar knee group (5.66° vs 2.1°) with p = 0.001.

INTERPRETATION

Rotating hinge knee prosthesis appears to represent a lower rotational constraint degree than constrained condylar knee systems in clinical practice and it may increase the clinical satisfaction. The clinical significance: Rotating hinge knee prosthesis appears to represent a lower constraint degree than constrained condylar knee systems in clinical practice.

View-independent gait events detection using CNN-transformer hybrid network

Accurate gait detection is crucial in utilizing the ample health information embedded in it. Vision-based approaches for gait detection have emerged as an alternative to the exacting sensor-based approaches, but their application has been rather limited due to complicated feature engineering processes and heavy reliance on lateral views. Thus, this study aimed to find a simple vision-based approach that is view-independent and accurate. A total of 22 participants performed six different actions representing standard and peculiar gaits, and the videos acquired from these actions were used as the input of the deep learning networks. Four networks, including a 2D convolutional neural network and an attention-based deep learning network, were trained with standard gaits, and their detection performance for both standard and peculiar gaits was assessed using measures including F1-scores. While all networks achieved remarkable detection performance, the CNN-Transformer network achieved the best performance for both standard and peculiar gaits. Little deviation by the speed of actions or view angles was found. The study is expected to contribute to the wider application of vision-based approaches in gait detection and gait-based health monitoring both at home and in clinical settings.

A non-contact system for intraoperative quantitative assessment of bradykinesia in deep brain stimulation surgery

BACKGROUND AND OBJECTIVE

Deep brain stimulation (DBS) is an effective treatment for a number of neurological diseases, especially for the advanced stage of Parkinson's disease (PD). Objective assessment of patients' motor symptoms is crucial for accurate electrode targeting and treatment. Existing approaches suffer from subjective variability or interference with voluntary motion. This work is aimed to establish an objective assessment system to quantify bradykinesia in DBS surgery.

METHODS

Based on the analysis of the requirements for intraoperative assessment, we developed a system with non-contact measurement, online movement feature extraction, and interactive data analysis and visualization. An optical sensor, Leap Motion Controller (LMC), was taken to detect hand movement in three clinical tasks. A graphic user interface was designed to process, compare and visualize the collected data and assessment results online. Quantified movement features include amplitude, frequency, velocity, their decrement and variability, etc. Technical validation of the system was performed with a motion capture system (Mocap), with respect to data-level and feature-level accuracy and reliability. Clinical validation was conducted with 20 PD patients for intraoperative assessments in DBS surgery. Treatment responses with respect to the bradykinesia movement features were analyzed. Single case analysis and group statistical analysis were performed to examine the differences between preoperative and intraoperative performance, and the correlation between the clinical ratings and the quantified assessment was analyzed.

RESULTS

For the movements measured by LMC and Mocap, the average Pearson's correlation coefficient was 0.986, and the mean amplitude difference was 2.11 mm. No significant difference was found for all movement features quantified by LMC and Mocap. For the clinical tests, key movement features showed significant differences between the preoperative baseline and intraoperative performance when the brain stimulation was ON. The assessment results were significantly correlated with the MDS-UPDRS clinical ratings.

CONCLUSIONS

The proposed non-contact system has established itself as an objective intraoperative assessment, analysis, and visualization tool for DBS treatment of Parkinson's disease.

Absolute Reliability of Gait Parameters Acquired With Markerless Motion Capture in Living Domains

Purpose: To examine the between-day absolute reliability of gait parameters acquired with Theia3D markerless motion capture for use in biomechanical and clinical settings. Methods: Twenty-one (7 M,14 F) participants aged between 18 and 73 years were recruited in community locations to perform two walking tasks: self-selected and fastest-comfortable walking speed. Participants walked along a designated walkway on two separate days.Joint angle kinematics for the hip, knee, and ankle, for all planes of motion, and spatiotemporal parameters were extracted to determine absolute reliability between-days. For kinematics, absolute reliability was examined using: full curve analysis [root mean square difference (RMSD)] and discrete point analysis at defined gait events using standard error of measurement (SEM). The absolute reliability of spatiotemporal parameters was also examined using SEM and SEM%. Results: Markerless motion capture produced low measurement error for kinematic full curve analysis with RMSDs ranging between 0.96° and 3.71° across all joints and planes for both walking tasks. Similarly, discrete point analysis within the gait cycle produced SEM values ranging between 0.91° and 3.25° for both sagittal and frontal plane angles of the hip, knee, and ankle. The highest measurement errors were observed in the transverse plane, with SEM >5° for ankle and knee range of motion. For the majority of spatiotemporal parameters, markerless motion capture produced low SEM values and SEM% below 10%. Conclusion: Markerless motion capture using Theia3D offers reliable gait analysis suitable for biomechanical and clinical use.

Using a Video Device and a Deep Learning-Based Pose Estimator to Assess Gait Impairment in Neurodegenerative Related Disorders: A Pilot Study

As the world’s population is living longer, age-related neurodegenerative diseases are becoming a more significant global issue. Neurodegenerative diseases cause worsening motor, cognitive and autonomic dysfunction over time and reduce functional abilities required for daily living. Compromised motor performance is one of the first and most evident manifestations. In the case of Parkinson’s disease, these impairments are currently evaluated by experts through the use of rating scales. Although this method is widely used by experts worldwide, it includes subjective and error-prone motor examinations that also fail in the characterization of symptoms’ fluctuations. The aim of this study is to evaluate whether artificial intelligence techniques can be used to objectively assess gait impairment in subjects with Parkinson’s disease. This paper presents the results of a cohort of ten subjects, five with a Parkinson’s disease diagnosis at different degrees of severity. We experimentally demonstrate good effectiveness of the proposed system in extracting the main features concerning people’s gait during the standard tests that clinicians use to assess the burden of disease. This system can offer neurologists, through accurate and objective data, a second opinion or a suggestion to reconsider score assignment. Thanks to its simplicity, tactful and non-intrusive approach and clinical-grade accuracy, it can be adopted on an ongoing basis even in environments where people usually live and work.

Vision-Based Gait Events Detection Using Deep Convolutional Neural Networks

Accurate gait events detection from the video would be a challenging problem. However, most vision-based methods for gait event detection highly rely on gait features that are estimated using gait silhouettes and human pose information for accurate gait data acquisition. This paper presented an accurate, multi-view approach with deep convolutional neural networks for efficient and practical gait event detection without requiring additional gait feature engineering. Especially, we aimed to detect gait events from frontal views as well as lateral views. We conducted the experiments with four different deep CNN models on our own dataset that includes three different walking actions from 11 healthy participants. Models took 9 subsequence frames stacking together as inputs, while outputs of models were probability vectors of gait events: toe-off and heel-strike for each frame. The deep CNN models trained only with video frames enabled to detect gait events with 93% or higher accuracy while the user is walking straight and walking around on both frontal and lateral views.

Remote Gait Type Classification System Using Markerless 2D Video

Several pathologies can alter the way people walk, i.e., their gait. Gait analysis can be used to detect such alterations and, therefore, help diagnose certain pathologies or assess people's health and recovery. Simple vision-based systems have a considerable potential in this area, as they allow the capture of gait in unconstrained environments, such as at home or in a clinic, while the required computations can be done remotely. State-of-the-art vision-based systems for gait analysis use deep learning strategies, thus requiring a large amount of data for training. However, to the best of our knowledge, the largest publicly available pathological gait dataset contains only 10 subjects, simulating five types of gait. This paper presents a new dataset, GAIT-IT, captured from 21 subjects simulating five types of gait, at two severity levels. The dataset is recorded in a professional studio, making the sequences free of background camouflage, variations in illumination and other visual artifacts. The dataset is used to train a novel automatic gait analysis system. Compared to the state-of-the-art, the proposed system achieves a drastic reduction in the number of trainable parameters, memory requirements and execution times, while the classification accuracy is on par with the state-of-the-art. Recognizing the importance of remote healthcare, the proposed automatic gait analysis system is integrated with a prototype web application. This prototype is presently hosted in a private network, and after further tests and development it will allow people to upload a video of them walking and execute a web service that classifies their gait. The web application has a user-friendly interface usable by healthcare professionals or by laypersons. The application also makes an association between the identified type of gait and potential gait pathologies that exhibit the identified characteristics.

A novel method for automatic classification of Parkinson gait severity using front-view video analysis

BACKGROUND

Gait impairment is an essential symptom of Parkinson's disease (PD).

OBJECTIVE

This paper introduces a novel computer-vision framework for automatic classification of the severity of gait impairment using front-view motion analysis.

METHODS

Four hundred and fifty-six videos were recorded from 19 PD patients using an RGB camera during clinical gait assessment. Gait performance in each video was rated by a neurologist using the unified Parkinson's disease rating scale for gait examination (UPDRS-gait). The proposed algorithm detects and tracks the silhouette of the test subject in the video to generate a height signal. Gait features were extracted from the height signal. Feature analysis was performed using the Kruskal-Wallis rank test. A support vector machine was trained using the features to classify the severity levels according to UPDRS-gait in 10-fold cross-validation.

RESULTS

Features significantly (p< 0.05) differentiated between median-ranks of UPDRS-gait levels. The SVM classified the levels with a promising area under the ROC of 80.88%.

CONCLUSION

Findings support the feasibility of this model for Parkinson's gait assessment in the home environment.

The knee prosthesis constraint dilemma: Biomechanical comparison between varus-valgus constrained implants and rotating hinge prosthesis. A cadaver study

The real degree of constriction of rotating hinge knee (RHK) and condylar constrained prostheses (CCK) is a matter of discussion in revision knee arthroplasty. The objectives of this study are to compare the tibial rotation of both implants and validate the use of inertial sensors with optical tracking system as movement measurement tools. A total of 16 cadaver knees were used. Eight knees were replaced using a RHK (Endomodel LINK), and the remaining eight received a CCK prosthesis (LCCK, Zimmer). Tibial rotation range of motion was measured in full extension and at 30°, 60°, and 90° of flexion, with four continuous waveforms for each measurement. Measurements were made using two inertial sensors with specific software and compared with measurements obtained using the gold standard technique - the motion capture camera. The comparison of the accuracy of both measurement methods showed no statistically significant differences between inertial sensors and motion capture cameras, with p > .1; the mean error for tibial rotation was 0.21°. Tibial rotation in the RHK was significantly greater than in the CCK (5.25° vs. 2.28°, respectively), p < .05. We have shown that RHK permit greater tibial rotation, being closer to physiological values than CCKs. Inertial sensors have been validated as an effective and accurate method of measuring knee movement. The clinical significance: RHK appears to represent a lower constriction degree than CCK systems.

Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification

Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.