Validation, Reliability, and Responsiveness Outcomes Of Kinematic Assessment With An RGB-D Camera To Analyze Movement In Subacute And Chronic Low Back Pain

Machine Learning-Based Computer Vision for Depth Camera-Based Physiotherapy Movement Assessment: A Systematic Review

Machine learning-based computer vision techniques using depth cameras have shown potential in physiotherapy movement assessment. However, a comprehensive understanding of their implementation, effectiveness, and limitations remains needed. Following PRISMA guidelines, we systematically reviewed studies from 2020 to 2024 across Web of Science, Scopus, PubMed, and Astrophysics Data System to explore recent advancements. From 371 initially identified publications, 18 met the inclusion criteria for detailed analysis. The analysis revealed three primary implementation scenarios: local (50%), clinical (33.4%), and remote (22.3%). Depth cameras, particularly the Kinect series (65.4%), dominated data collection methods. Data processing approaches primarily utilized RGB-D (55.6%) and skeletal data (27.8%), with algorithms split between traditional machine learning (44.4%) and deep learning (41.7%). Key challenges included limited real-world validation, insufficient dataset diversity, and algorithm generalization issues, while machine learning-based computer vision systems demonstrated effectiveness in movement assessment tasks, further research is needed to address validation in clinical settings and improve algorithm generalization. This review provides a foundation for enhancing computer vision-based assessment tools in physiotherapy practice.

Assessment of Spinal and Pelvic Kinematics Using Inertial Measurement Units in Clinical Subgroups of Persistent Non-Specific Low Back Pain

Inertial measurement units (IMUs) offer a portable and quantitative solution for clinical movement analysis. However, their application in non-specific low back pain (NSLBP) remains underexplored. This study compared the spine and pelvis kinematics obtained from IMUs between individuals with and without NSLBP and across clinical subgroups of NSLBP. A total of 81 participants with NSLBP with flexion (FP; n = 38) and extension (EP; n = 43) motor control impairment and 26 controls (No-NSLBP) completed 10 repetitions of spine movements (flexion, extension, lateral flexion). IMUs were placed on the sacrum, fourth and second lumbar vertebrae, and seventh cervical vertebra to measure inclination at the pelvis, lower (LLx) and upper (ULx) lumbar spine, and lower cervical spine (LCx), respectively. At each location, the range of movement (ROM) was quantified as the range of IMU orientation in the primary plane of movement. The ROM was compared between NSLBP and No-NSLBP using unpaired t-tests and across FP-NSLBP, EP-NSLBP, and No-NSLBP subgroups using one-way ANOVA. Individuals with NSLBP exhibited a smaller ROM at the ULx (p = 0.005), LLx (p = 0.003) and LCx (p = 0.01) during forward flexion, smaller ROM at the LLx during extension (p = 0.03), and a smaller ROM at the pelvis during lateral flexion (p = 0.003). Those in the EP-NSLBP group had smaller ROM than those in the No-NSLBP group at LLx during forward flexion (Bonferroni-corrected p = 0.005), extension (p = 0.013), and lateral flexion (p = 0.038), and a smaller ROM at the pelvis during lateral flexion (p = 0.005). Those in the FP-NSLBP subgroup had smaller ROM than those in the No-NSLBP group at the ULx during forward flexion (p = 0.024). IMUs detected variations in kinematics at the trunk, lumbar spine, and pelvis among individuals with and without NSLBP and across clinical NSLBP subgroups during flexion, extension, and lateral flexion. These findings consistently point to reduced ROM in NSLBP. The identified subgroup differences highlight the potential of IMU for assessing spinal and pelvic kinematics in these clinically verified subgroups of NSLBP.

Dynamic assessment of spine movement patterns using an RGB-D camera and deep learning

In clinical practice, functional limitations in patients with low back pain are subjectively assessed, potentially leading to misdiagnosis and prolonged pain. This paper proposes an objective deep learning (DL) markerless motion capture system that uses a red-green-blue-depth (RGB-D) camera to measure the kinematics of the spine during flexion-extension (FE) through: 1) the development and validation of a DL semantic segmentation algorithm that segments the back into four anatomical classes and 2) the development and validation of a framework that uses these segmentations to measure spine kinematics during FE. Twenty participants performed ten cycles of FE with drawn-on point markers while being recorded with an RGB-D camera. Five of these participants also performed an additional trial where they were recorded with an optical motion capture (OPT) system. The DL algorithm was trained to segment the back and pelvis into four anatomical classes: upper back, lower back, spine, and pelvis. A kinematic framework was then developed to refine these segmentations into upper spine, lower spine, and pelvis masks, which were used to measure spine kinematics after obtaining 3D global coordinates of the mask corners. The segmentation algorithm achieved high accuracy, and the root mean square error (RMSE) between ground truth and predicted lumbar kinematics was < 4°. When comparing markerless and OPT kinematics, RMSE values were < 6°. This work demonstrates the feasibility of using markerless motion capture to assess FE spine movement in clinical settings. Future work will expand the studied movement directions and test on different demographics.

The Reliability and Validity of the Lie-to-Sit-to-Stand-to-Walk Transfer (LSSWT) Test in Knee Osteoarthritis

BACKGROUND

Several neuromuscular impairments may be observed in older patients with knee osteoarthritis (OA), increasing the risk of falling, which is common during transfer activities. The Lie-to-Sit-to- Stand-to-Walk Transfer (LSSWT) test was developed to evaluate complex transfer abilities. The study aims to investigate the reliability and validity of LSSWT in patients with knee OA.

METHODS

Twenty-nine patients with knee OA were included in this study. The LSSWT, Timed up and go test (TUG), and Western Ontario and McMaster Universities Arthritis Index (WOMAC) were administered to the patients. Patients rested for at least an hour between the trials to avoid fatigue.

RESULTS

The LSSWT has excellent reliability and high validity in patients with knee OA. The relative (ICC coefficient) and absolute (SEM and SRD95) reliability values are 0.96 (95% CI: 0.91-0.98), 1.00, and 2,75, respectively. The Pearson correlation coefficient of the LSSWT with the TUG is 0.73 (p < 0.01), and the Spearmen correlation coefficient of the LSSWT with the WOMAC is 0.54 (p < 0.05).

CONCLUSIONS

The LSSWT is highly reliable and valid in knee OA and is recommended for routine dynamic balance establishment. Having a low minimal clinically important difference shows the LSSWT's sensitivity. The LSSWT can easily identify dynamic balance deficits in knee OA patients and help prevent fall incidents.

Reliability and Validity of Inertial Sensor Assisted Reaction Time Measurement Tools among Healthy Young Adults

The assessment of movement reaction time (RT) as a sideline assessment is a valuable biomarker for mild TBI or concussion. However, such assessments require controlled laboratory environments, which may not be feasible for sideline testing during a game. Body-worn wearable devices are advantageous as being cost-effective, easy to don and use, wirelessly transmit data, and ensure unhindered movement performance. This study aimed to develop a Drop-stick Test System (DTS) with a wireless inertial sensor and confirm its reliability for different standing conditions (Foam versus No Foam) and task types (Single versus Dual), and postures (Standing versus sitting). Fourteen healthy young participants (seven females, seven males; age 24.7 ± 2.6 years) participated in this study. The participants were asked to catch a falling stick attached to the sensor during a drop test. Reaction Times (RTs) were calculated from data for each trial from DTS and laboratory camera system (gold standard). Intraclass correlation coefficients (ICC 3,k) were computed to determine inter-instrument reliability. The RT measurements from participants using the camera system and sensor-based DTS showed moderate to good inter-instrument reliability with an overall ICC of 0.82 (95% CI 0.78-0.85). Bland-Altman plots and 95% levels of agreement revealed a bias where the DTS underestimated RT by approximately 50 ms.

A Robust 3D-Based Color Correction Approach for Texture Mapping Applications

Texture mapping of 3D models using multiple images often results in textured meshes with unappealing visual artifacts known as texture seams. These artifacts can be more or less visible, depending on the color similarity between the used images. The main goal of this work is to produce textured meshes free of texture seams through a process of color correcting all images of the scene. To accomplish this goal, we propose two contributions to the state-of-the-art of color correction: a pairwise-based methodology, capable of color correcting multiple images from the same scene; the application of 3D information from the scene, namely meshes and point clouds, to build a filtering procedure, in order to produce a more reliable spatial registration between images, thereby increasing the robustness of the color correction procedure. We also present a texture mapping pipeline that receives uncorrected images, an untextured mesh, and point clouds as inputs, producing a final textured mesh and color corrected images as output. Results include a comparison with four other color correction approaches. These show that the proposed approach outperforms all others, both in qualitative and quantitative metrics. The proposed approach enhances the visual quality of textured meshes by eliminating most of the texture seams.

Human motion capture for movement limitation analysis using an RGB-D camera in spondyloarthritis: a validation study

A human motion capture system using an RGB-D camera could be a good option to understand the trunk limitations in spondyloarthritis. The aim of this study is to validate a human motion capture system using an RGB-D camera to analyse trunk movement limitations in spondyloarthritis patients. Cross-sectional study was performed where spondyloarthritis patients were diagnosed with a rheumatologist. The RGB-D camera analysed the kinematics of each participant during seven functional tasks based on rheumatologic assessment. The OpenNI2 library collected the depth data, the NiTE2 middleware detected a virtual skeleton and the MRPT library recorded the trunk positions. The gold standard was registered using an inertial measurement unit. The outcome variables were angular displacement, angular velocity and lineal acceleration of the trunk. Criterion validity and the reliability were calculated. Seventeen subjects (54.35 (11.75) years) were measured. The Bending task obtained moderate results in validity (r = 0.55-0.62) and successful results in reliability (ICC = 0.80-0.88) and validity and reliability of angular kinematic results in Chair task were moderate and (r = 0.60-0.74, ICC = 0.61-0.72). The kinematic results in Timed Up and Go test were less consistent. The RGB-D camera was documented to be a reliable tool to assess the movement limitations in spondyloarthritis depending on the functional tasks: Bending task. Chair task needs further research and the TUG analysis was not validated. Comparation of both systems, required software for camera analysis, outcomes and final results of validity and reliability of each test.

Balance Measurement Using Microsoft Kinect v2: Towards Remote Evaluation of Patient with the Functional Reach Test

To prevent falls, it is important to measure periodically the balance ability of an individual using reliable clinical tests. As Red Green Blue Depth (RGBD) devices have been increasingly used for balance rehabilitation at home, they may also be used to assess objectively the balance ability and determine the effectiveness of a therapy. For this, we developed a system based on the Microsoft Kinect v2 for measuring the Functional Reach Test (FRT); one of the most used balance clinical tools to predict falls. Two experiments were conducted to compare the FRT measures computed by our system using the Microsoft Kinect v2 with those obtained by the standard method, i.e., manually. In terms of validity, we found a very strong correlation between the two methods (r = 0.97 and r = 0.99 (p < 0.05), for experiments 1 and 2, respectively). However, we needed to correct the measurements using a linear model to fit the data obtained by the Kinect system. Consequently, a linear regression model has been applied and examining the regression assumptions showed that the model works well for the data. Applying the paired t-test to the data after correction indicated that there is no statistically significant difference between the measurements obtained by both methods. As for the reliability of the test, we obtained good to excellent within repeatability of the FRT measurements tracked by Kinect (ICC = 0.86 and ICC = 0.99, for experiments 1 and 2, respectively). These results suggested that the Microsoft Kinect v2 device is reliable and adequate to calculate the standard FRT.

Differences in movement limitations in different low back pain severity in functional tests using an RGB-D camera

Low back pain (LBP) can lead to motor control disturbance which can be one of the causes of reoccurrence of the complaint. It is important to improve our knowledge of movement related disturbances during assessment in LBP and to classify patients according to the severity. The aim of this study is to present differences in kinematic variables using a RGB-D camera in order to classify LBP patients with different severity. A cross-sectional study was carried out. Subjects with non-specific subacute and chronic LBP were screened 6 weeks following an episode. Functional tests were bending trunk test, sock test and sit to stand test. Participants performed as many repetitions as possible during 30 s for each functional test. Angular displacement, velocity and acceleration, linear acceleration, time and repetitions were analysed. Participants were divided into two groups to determine their different LBP severity with a k-means clusters according to the results obtained in Roland Morris questionnaire (RMQ). Comparing different severity groups based on RMQ score (high impact = 17.15, low impact = 7.47), bending trunk test obtained significative differences in linear acceleration (p = 0.002-0.01). The differences of total linear acceleration during the Sit to Stand test were significative (p = 0.004-0.02). Sock test showed not significative differences between groups (p > 0.05). Linear acceleration variables during Sit to Stand test and Bending trunk test were significatively different between the different severity groups. RGB-D camera system and functional tests can detect kinematic differences in different type of LBP according to the functionality. Trial registration: ClinicalTrials.gov NCT03293095 "Functional Task Kinematic in Musculoskeletal Pathology" September 26, 2017.

Enhancement of RGB-D Image Alignment Using Fiducial Markers

Three-dimensional (3D) reconstruction methods generate a 3D textured model from the combination of data from several captures. As such, the geometrical transformations between these captures are required. The process of computing or refining these transformations is referred to as alignment. It is often a difficult problem to handle, in particular due to a lack of accuracy in the matching of features. We propose an optimization framework that takes advantage of fiducial markers placed in the scene. Since these markers are robustly detected, the problem of incorrect matching of features is overcome. The proposed procedure is capable of enhancing the 3D models created using consumer level RGB-D hand-held cameras, reducing visual artefacts caused by misalignments. One problem inherent to this solution is that the scene is polluted by the markers. Therefore, a tool was developed to allow their removal from the texture of the scene. Results show that our optimization framework is able to significantly reduce alignment errors between captures, which results in visually appealing reconstructions. Furthermore, the markers used to enhance the alignment are seamlessly removed from the final model texture.