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.

A data-driven framework for assessing soldier performance, health, and survivability.

Presented is a framework that uses pattern classification methods to incrementally morph whole-body movement patterns to investigate how personal (sex, military experience, and body mass) and load characteristics affect the survivability tradespace: performance, musculoskeletal health, and susceptibility to enemy action. Sixteen civilians and 12 soldiers performed eight military-based movement patterns under three body-borne loads: ∼5.5 kg, ∼22 kg, and ∼38 kg. Our framework reduces dimensionality using principal component analysis and uses linear discriminant analysis to classify groups and morph movement patterns. Our framework produces morphed whole-body movement patterns that emulate previously published changes to the survivability tradespace caused by body-borne loads. Additionally, we identified that personal characteristics can greatly impact the tradespace when carrying heavy body-borne loads. Using our framework, military leaders can make decisions based on objective information for armour procurement, employment of armour, and battlefield performance, which can positively impact operational readiness and increase overall mission success.

Beyond the mechanical lens: Systemic inflammatory responses to repetitive lifting under varying loads and frequencies.

OBJECTIVE: Currently, low back disorder (LBD) research focuses primarily on mechanical variables to assess whether task demands exceed tissue capacity; however, it is important to assess how other nonmechanical variables affect tissue capacity in a time-dependent manner. The current investigation sought to explore physiological responses to an acute lifting task, as lifting has been implicated as a risk factor in the development of LBDs. METHODS: Twelve participants completed two sessions of 2 h of repetitive symmetrical lifting from floor to knuckle height under two conditions, matched for total external work (Low Force High Repetition (LFHR) and High Force Low Repetition (HFLR)). Full-body kinematics and ground reaction forces were measured throughout. Interleukin 6 (IL-6) and interleukin 8 (IL-8), markers of systemic inflammation, were assessed from blood sampling at Baseline, 0, 4 and 24 h post-lifting on both days. Dual x-ray absorptiometry (DEXA) scans were also performed on participants to quantify body composition. RESULTS: Significant load (HFLR and LFHR) * time (Baseline, 0, 4, 24 h) interaction effects were found for both IL-6 and IL-8, where the LFHR condition resulted in greater responses at 0 and 4 h post-lifting. CONCLUSIONS: This was the first study of its kind to concurrently measure peak and cumulative spinal moments and their relationship to systemic inflammation in both sexes, while strictly controlling for confounding variables (e.g. physical activity, caloric intake, body composition, etc.). Greater levels of IL-6 and IL-8 were seen in the LFHR condition, likely due to the greater cumulative spinal moments in this condition.

Validation of an IMU Suit for Military-Based Tasks.

Investigating the effects of load carriage on military soldiers using optical motion capture is challenging. However, inertial measurement units (IMUs) provide a promising alternative. Our purpose was to compare optical motion capture with an Xsens IMU system in terms of movement reconstruction using principal component analysis (PCA) using correlation coefficients and joint kinematics using root mean squared error (RMSE). Eighteen civilians performed military-type movements while their motion was recorded using both optical and IMU-based systems. Tasks included walking, running, and transitioning between running, kneeling, and prone positions. PCA was applied to both the optical and virtual IMU markers, and the correlations between the principal component (PC) scores were assessed. Full-body joint angles were calculated and compared using RMSE between optical markers, IMU data, and virtual markers generated from IMU data with and without coordinate system alignment. There was good agreement in movement reconstruction using PCA; the average correlation coefficient was 0.81 ± 0.14. RMSE values between the optical markers and IMU data for flexion-extension were less than 9°, and 15° for the lower and upper limbs, respectively, across all tasks. The underlying biomechanical model and associated coordinate systems appear to influence RMSE values the most. The IMU system appears appropriate for capturing and reconstructing full-body motion variability for military-based movements.

The effect of head and gaze orientation on spine kinematics during forward flexion.

Compound, or awkward, spine postures have been suggested as a biomechanical risk factor for low back injury. This experiment investigates the influence of head (i.e. head-on-torso) and gaze (i.e. eye-in-head) orientation on three-dimensional (3D) neck and spine range of motion (ROM) during forward flexion movements. To emulate previous experimental protocols and replicate real-world scenarios, a sample of ten young, healthy males (mean ± standard deviation: age: 20.8 ± 1.03 years, height: 180.2 ± 7.36 cm, and mass: 81.9 ± 6.47 kg) completed forward flexion movements with a constrained and unconstrained pelvis, respectively. Surface kinematics were gathered from the head and spine (C7-S1). Movements were completed under a baseline condition as well as upward, downward, leftward, and rightward head and gaze orientations. For each condition, mean neck angle and inter-segmental spine (C7T1 through L5S1) ROM were evaluated. The results demonstrate that directed head and gaze orientations can influence the ROM of specific spine regions during a forward flexion task. With leftward and rightward directed head and gaze orientations, the neck became increasingly twisted and superior thoracic segments (i.e. C7T1-T2T3) were significantly more twisted during the leftward head orientation condition than the baseline condition. With upward and downward directed head and gaze orientations, a similar effect was observed for neck and superior thoracic (i.e. C7T1-T4T5) flexion-extension. Interestingly, it was also demonstrated that changes in upward/downward head orientation can also change flexion-extension kinematics of the thoracolumbar region as well (i.e. T7T8-L1L2), suggesting that head postures requiring neck extension may also promote extension throughout these spine regions. These findings provide evidence for a functional link between changes in neck flexion-extension posture and flexion-extension movement of the thoracolumbar region of the spine.

The effects of protective footwear on spine control and lifting mechanics.

Manual materials handling is often performed in hazardous environments where protective footwear must be worn; however, workers can wear different types of footwear depending on the hazards present. Therefore, the goal of this study was to investigate how three-dimensional lifting mechanics and trunk local dynamic stability are affected by different types of protective footwear (i.e. steel-toed shoes (unlaced boot), steel-toed boots (work boot), and steel-toed boots with a metatarsal guard (MET)). Twelve males and twelve females performed a repetitive lifting task at 10% of their maximum lifting effort, under three randomized footwear conditions. Footwear type influenced ankle range of motion (ROM). The work boot condition reduced ankle sagittal ROM (p = 0.007) and the MET condition reduced ankle ROM in the sagittal (p = 0.004), frontal (p = 0.001) and transverse (p = 0.003) planes. Despite these differences at the ankle, no other changes in participant lifting mechanics were observed.

The effect of attentional focus on local dynamic stability during a repetitive spine flexion task.

The association between low back pain and spine movement control suggests that it is important to reliably quantify movement behavior. One method to characterize spine movement behavior is to measure the local dynamic stability (LDS) of spine movement during a repetitive flexion task in which a participant is asked to touch multiple targets repetitively. Within the literature, it has been well established that an individual's focus of attention (FOA) can modulate their neuromuscular control and affect task performance. The goal of this project was to examine the unknown effect of FOA on LDS measurements and timing error during a repetitive spine flexion task that is commonly used to assess movement control. Fourteen healthy adults (7 male) were instructed to touch two targets (shoulder height and knee height) to the beat of a metronome (4 s/cycle) for 35 consecutive cycles. They completed this task under internal (focus on trunk movement) and external (focus on targets) FOA conditions. Motion capture data of the trunk and sacrum were collected at 120 Hz. The lumbar spine angle was defined as the orientation of the trunk relative to the pelvis. The local divergence exponent (λmax) was calculated from the sum of squares of the 3-dimensional spine angle. Timing error was calculated as the time difference between target touches and metronome beats. Changing an individual's FOA had no effect on λmax calculations or timing error. Although clear task instructions are important, it is not essential to control for FOA during this movement assessment protocol.

The effects of weighted skates on ice-skating kinematics, kinetics and muscular activity.

Sport-specific resistance training, through limb loading, can be a complimentary training method to traditional resistance training by loading the working muscles during all phases of a specific movement. The purpose of this study was to examine the acute effects of skating with an additional load on the skate, using a skate weight prototype, on kinematics, kinetics, and muscle activation during the acceleration phase while skating on a synthetic ice surface. 10 male hockey skaters accelerated from rest (standing erect with knees slightly bent) under four non-randomized load conditions: baseline 1 (no weight), light (0.9 kg per skate), heavy (1.8 kg per skate), and baseline 2 (no weight). Skating with additional weight caused athletes to skate slower (p < 0.001; η2 = 0.551), and led to few changes in kinematics: hip sagittal range of motion (ROM) decreased (2.2°; p = 0.032; η2 = 0.274), hip transverse ROM decreased (3.4°; p < 0.001; η2 = 0.494), ankle sagittal ROM decreased (2.3°; p = 0.022; η2 = 0.295), and knee sagittal ROM increased (7.8°; p < 0.001, η2 = 0.761). Overall, weighted skates decreased skating velocity, but athletes maintained similar muscle activation profiles (magnitude and trends) with minor changes to their skating kinematics.

Exploring the relationship between local and global dynamic trunk stabilities during repetitive lifting tasks.

Lifting is a major risk factor for low back injury. Lifters experience small continual perturbations, because moving a load provides a disturbance to the lifter׳s equilibrium. The goal of the present study was to examine the relationship between local and global trunk/spine stabilities during external perturbations introduced at the foot-floor interface. 12 healthy males were recruited to participate in this study. Participants completed a freestyle lifting protocol on a perturbation treadmill, under three randomized load conditions: ~0, 4, and 8 kg. Participants performed a total of 40 lifts under each load condition; no perturbations occurred during the first 20 lifts. During the last 20 lift cycles (in blocks of 5) the participants were randomly perturbed. Local dynamic trunk stability was quantified using the local divergence exponent (λmax) of the first 20 lifts. In addition, the distance traveled from the unperturbed lifting pattern (B), the time to max distance (Tau), the relaxation distance (A), and the rate of return toward the normal lifting pattern (Beta) were analyzed following each external perturbation. An increase in lifted load lead to significantly increased local trunk stability (p=0.046). Higher load also lead to decreased distance (B) traveled away from the unperturbed trajectory (p=0.023). Results agree with previous research that increasing load lifted significantly improves local trunk/spine stability during lifting. Here we have shown that altered local stability also translates into a greater ability to resist external global perturbations, which may reduce injury risk and should be explored in the future.