Optical Motion Tracking System Research Articles

A digital approach to fabricating a custom holder for the attachment of a mandibular sensor of an optical jaw motion tracking system: A dental technique

A digital approach to fabricating a custom holder to attach a mandibular sensor of an optical jaw motion tracking system is described. Typically, jaw motion tracking systems come with standard holders. However, additional chairside time is still required to adapt the holder's arm to the individual arch and securely attach the holder to the mandibular teeth. Moreover, the placement of the standard holder is problematic in patients with a deep vertical overlap or with short clinical crowns. This technique offers a digital approach to designing and fabricating a custom holder in situations where standard holders cannot be efficiently attached. The custom holder is designed to accommodate the available space without interfering with the occlusion, thereby minimizing the time needed to attach the holder and optimizing the workflow for clinical jaw motion tracking.

Remote Gait Analysis Using Ultra-Wideband Radar Technology Based on Joint Range-Doppler-Time Representation.

In recent years, radar technology has been extensively utilized in contactless human behavior monitoring systems. The unique capabilities of ultra-wideband (UWB) radars compared to conventional radar technologies, due to time-of-flight measurements, present new untapped opportunities for in-depth monitoring of human movement during overground locomotion. This study aims to investigate the deployability of UWB radars in accurately capturing the gait patterns of healthy individuals with no known walking impairments. A novel algorithm was developed that can extract ten clinical spatiotemporal gait features using the Doppler information captured from three monostatic UWB radar sensors during a 6-meter walking task. Key gait events are detected from lower-extremity movements based on the joint range-Doppler-time representation of recorded radar data. The estimated gait parameters were validated against a gold-standard optical motion tracking system using 12 healthy volunteers. On average, nine gait parameters can be consistently estimated with 90-98% accuracy, while capturing 94.5% of participants' gait variability and 90.8% of inter-limb symmetry. Correlation and Bland-Altman analysis revealed a strong correlation between radar-based parameters and the ground-truth values, with average discrepancies consistently close to 0. Results prove that radar sensing can provide accurate biomarkers to supplement clinical human gait assessment, with quality similar to gold standard assessment. Radars can potentially allow a transition from expensive and cumbersome lab-based gait analysis tools toward a completely unobtrusive and affordable solution for in-home deployment, enabling continuous long-term monitoring of individuals for research and healthcare applications.

Predicting object properties based on movement kinematics

In order to grasp and transport an object, grip and load forces must be scaled according to the object’s properties (such as weight). To select the appropriate grip and load forces, the object weight is estimated based on experience or, in the case of robots, usually by use of image recognition. We propose a new approach that makes a robot’s weight estimation less dependent on prior learning and, thereby, allows it to successfully grasp a wider variety of objects. This study evaluates whether it is feasible to predict an object’s weight class in a replacement task based on the time series of upper body angles of the active arm or on object velocity profiles. Furthermore, we wanted to investigate how prediction accuracy is affected by (i) the length of the time series and (ii) different cross-validation (CV) procedures. To this end, we recorded and analyzed the movement kinematics of 12 participants during a replacement task. The participants’ kinematics were recorded by an optical motion tracking system while transporting an object, 80 times in total from varying starting positions to a predefined end position on a table. The object’s weight was modified (made lighter and heavier) without changing the object’s visual appearance. Throughout the experiment, the object’s weight (light/heavy) was randomly changed without the participant’s knowledge. To predict the object’s weight class, we used a discrete cosine transform to smooth and compress the time series and a support vector machine for supervised learning from the achieved discrete cosine transform parameters. Results showed good prediction accuracy (up to 95%, depending on the CV procedure and the length of the time series). Even at the beginning of a movement (after only 300 ms), we were able to predict the object weight reliably (within a classification rate of 88-94%).

An Integrated Approach for Real-Time Monitoring of Knee Dynamics with IMUs and Multichannel EMG.

Measuring human joint dynamics is crucial for understanding how our bodies move and function, providing valuable insights into biomechanics and motor control. Cerebral palsy (CP) is a neurological disorder affecting motor control and posture, leading to diverse gait abnormalities, including altered knee angles. The accurate measurement and analysis of knee angles in individuals with CP are crucial for understanding their gait patterns, assessing treatment outcomes, and guiding interventions. This paper presents a novel multimodal approach that combines inertial measurement unit (IMU) sensors and electromyography (EMG) to measure knee angles in individuals with CP during gait and other daily activities. We discuss the performance of this integrated approach, highlighting the accuracy of IMU sensors in capturing knee joint movements when compared with an optical motion-tracking system and the complementary insights offered by EMG in assessing muscle activation patterns. Moreover, we delve into the technical aspects of the developed device. The presented results show that the angle measurement error falls within the reported values of the state-of-the-art IMU-based knee joint angle measurement devices while enabling a high-quality EMG recording over prolonged periods of time. While the device was designed and developed primarily for measuring knee activity in individuals with CP, its usability extends beyond this specific use-case scenario, making it suitable for applications that involve human joint evaluation.

Development of a 6-DOF Parallel Robot for Potential Single-Incision Laparoscopic Surgery Application

This paper presents the development of a 6-DOF (Degrees of Freedom) parallel robot for single-incision laparoscopic surgery (SILS). The concept of the robotic system is developed with respect to a medical protocol designed by the medical experts in the team targeting a SILS procedure in urology. The kinematic model of the robotic system was defined to determine the singularities that may occur during functioning. FEM analyses were performed to determine the components of the robotic structure that may compromise the rigidity of the robotic system, and these components were redesigned and integrated into the final design of the robot. To verify the kinematic model a series of numerical and graphical simulations were performed, while to test the functionality of the robotic system, a low-cost experimental model was developed. The accuracy of the experimental model was measured using an optical motion tracking system.

Comparison of thoracolumbar spine kinematics and injuries in reclined frontal impact sled tests between mid-size adult female and male PMHS

Disparities in injury tolerance and kinematic response remain understudied despite field data highlighting sex-based differences in injury risk. Furthermore, the automotive industry anticipates occupants will prefer reclined seating in highly automated vehicles. This study aimed to compare thoracolumbar spine kinematics and injuries between mid-size female and male post-mortem human subjects (PMHS) in reclined frontal impacts. Seven adult PMHS (three female, four male) were tested in reclined (50°) 50 km/h frontal impacts. The PMHS were seated on a semi-rigid seat and restrained by a prototype three-point seat belt system designed to mitigate submarining. The 3-D motions of five vertebrae and the pelvis were measured by an optical motion tracking system. Pressure transducers were inserted into intervertebral discs at three locations along the lumbar spine to track timing of lumbar vertebra fractures. Due to variations in the geometry of the pelvis and soft tissue surrounding the pelvis compared to the male subjects, the female subjects could not be positioned in the seat the same as the males, and, as a result, the females and their belt anchors needed to be translated forward in the seat to maintain similar belt geometry relative to the males. The females exhibited similar pre-test spinal curvatures and kinematics to the males. An L1 fracture was observed in one of three female subjects and two of four male subjects, and timing of these fractures were both similar (61 ∼ 65 ms) and close to the time of peak downward seat force. Generally, the female and male subjects exhibited similar kinematic and injury responses in this reclined frontal impact sled test condition.

Inertial sensors for gait monitoring and design of adaptive controllers for exoskeletons after stroke: a feasibility study.

Introduction: Tuning the control parameters is one of the main challenges in robotic gait therapy. Control strategies that vary the control parameters based on the user's performance are still scarce and do not exploit the potential of using spatiotemporal metrics. The goal of this study was to validate the feasibility of using shank-worn Inertial Measurement Units (IMUs) for clinical gait analysis after stroke and evaluate their preliminary applicability in designing an automatic and adaptive controller for a knee exoskeleton (ABLE-KS). Methods: First, we estimated the temporal (i.e., stride time, stance, and swing duration) and spatial (i.e., stride length, maximum vertical displacement, foot clearance, and circumduction) metrics in six post-stroke participants while walking on a treadmill and overground and compared these estimates with data from an optical motion tracking system. Next, we analyzed the relationships between the IMU-estimated metrics and an exoskeleton control parameter related to the peak knee flexion torque. Finally, we trained two machine learning algorithms, i.e., linear regression and neural network, to model the relationship between the exoskeleton torque and maximum vertical displacement, which was the metric that showed the strongest correlations with the data from the optical system [r = 0.84; ICC(A,1) = 0.73; ICC(C,1) = 0.81] and peak knee flexion torque (r = 0.957). Results: Offline validation of both neural network and linear regression models showed good predictions (R2 = 0.70-0.80; MAE = 0.48-0.58Nm) of the peak torque based on the maximum vertical displacement metric for the participants with better gait function, i.e., gait speed > 0.7m/s. For the participants with worse gait function, both models failed to provide good predictions (R2 = 0.00-0.19; MAE = 1.15-1.29Nm) of the peak torque despite having a moderate-to-strong correlation between the spatiotemporal metric and control parameter. Discussion: Our preliminary results indicate that the stride-by-stride estimations of shank-worn IMUs show potential to design automatic and adaptive exoskeleton control strategies for people with moderate impairments in gait function due to stroke.

Range of rotation of thoracolumbar vertebrae in Japanese macaques.

In humans, the range of thoracic vertebral rotation is known to be greater than that of the lumbar vertebrae due to their zygapophyseal orientation and soft tissue structure. However, little is known regarding vertebral movements in non-human primate species, which are primarily quadrupedal walkers. To understand the evolutionary background of human vertebral movements, this study estimated the range of axial rotation of the thoracolumbar spine in macaque monkeys. First, computed tomography (CT) was performed while passively rotating the trunk of whole-body cadavers of Japanese macaques, after which the motion of each thoracolumbar vertebra was estimated. Second, to evaluate the influence of the shoulder girdle and surrounding soft tissues, specimens with only bones and ligaments were prepared, after which the rotation of each vertebra was estimated using an optical motion tracking system. In both conditions, the three-dimensional coordinates of each vertebra were digitized, and the axial rotational angles between adjacent vertebrae were calculated. In the whole-body condition, the lower thoracic vertebrae had a greater range of rotation than did the other regions, similar to that observed in humans. In addition, absolute values for the range of rotation were similar between humans and macaques. However, in the bone-ligament preparation condition, the upper thoracic vertebrae had a range of rotation similar to that of the lower thoracic vertebrae. Contrary to previous speculations, our results showed that the mechanical restrictions by the ribs were not as significant; rather, the shoulder girdle largely restricted the rotation of the upper thoracic vertebrae, at least, in macaques.

The effects of the size and strength of food on jaw motion and temporomandibular joints.

Mastication displays much importance in people's lives. The masticatory mandibular motion associated with dental kinematics also impacts temporomandibular joint (TMJ) kinematics and even TMJ health status. How food properties impact kinematical parameters of TMJs is a meaningful question for the conservative treatment of temporomandibular disorders (TMD) and evidence for the diet recommendation of TMD patients. The aim of this study was to find the primary mechanical properties influencing the masticatory motion. The potato boluses with different boiling times and sizes were chosen. The optical motion tracking system was adopted to record the masticatory trials of chewing boluses with various mechanical properties. The mechanical experiments revealed that increasing boiling time could reduce compressive strength. Moreover, multiple regression models were built to find the primary property of food influencing the TMJ kinematics, including condylar displacement, velocity, acceleration, and crushing time. The results showed that the bolus size had a significant primary influence on condylar displacements. The chewing times had a significantly minor influence on condylar displacements, while bolus strength had only a small impact on condylar displacements. Furthermore, condylar displacements on the non-working side were more affected by bolus size and chewing times than on the working sides. The crushing time of the bolus was significantly influenced by the compressive strength. Meals with small sizes and soft properties were therefore advised to lessen condylar displacements and relax the crushing process, and further reduce the loadings in the TMJ.

BIOMECHANICAL EVALUATION OF AN ALLOGRAFT FIXATION SYSTEM FOR ANTERIOR CRUCIATE LIGAMENT RECONSTRUCTION IN COMPARISON WITH THE INTERFERENCE SCREW

Screw fixation is an established method for anterior cruciate ligament (ACL) reconstruction, although with a high rate of implant-related complications. An allograft system for implant fixation in ACL reconstruction, the Shark Screw ACL (surgebright GmbH) could overcome some of the shortcomings of bioabsorbable screws, such as foreign body reaction, need for implant removal and imaging artefacts. However, it needs to provide sufficient mechanical stability. Therefore, the aim of this study was to investigate the biomechanical stability, especially graft slippage, of the novel allograft system versus a conventional bioabsorbable interference screw (BioComposite Interference Screw; Arthrex Inc.) for tibial implant fixation in ACL reconstruction.Twenty-four paired human proximal tibiae (3 female, 9 male, 72.7 ± 5.6 years) underwent ACL reconstruction. The quadrupled semitendinosus and gracilis tendon graft were fixed in one specimen of each pair using the allograft fixation system Shak Screw ACL and the contralateral one using an interference screw. All specimens were cyclically loaded at 1 Hz with peak load levels monotonically increased from 50 N at a rate of 0.1 N/cycle until catastrophic failure. Relative movements of the graft versus the tibia were captured with a stereographic optical motion tracking system (Aramis SRX; GOM GmbH).The two fixation methods did not demonstrate any statistical difference in ultimate load at graft slippage (p = 0.24) or estimated survival at slippage (p = 0.06). Both, the ultimate load and estimated survival until failure were higher in the interference screw (p = 0.04, and p = 0.018, respectively). Graft displacement at ultimate load reached values of up to 7.2 mm (interference screw) and 11.3 mm (Shark Screw ACL).The allograft screw for implant fixation in ACL reconstruction showed similar behavior in terms of graft slippage compared to the conventional metal interference screw but underperformed in terms of ultimate load. However, the ultimate load may not be considered a direct indicator of clinical failure.

Inertial Measurement Units’ Reliability for Measuring Knee Joint Angle during Road Cycling

We explore the reliability of joint angles in road cycling obtained using inertial measurement units. The considered method relies on 3D accelerometer and gyroscope measurements obtained from two such units, appropriately attached to two adjacent body parts, measuring the angle of the connecting joint. We investigate the effects of applying a simple drift compensation technique and an error-state Kalman filter. We consider the knee joint angle in particular, and conduct two measurement trials, a 5 and a 20 minute one, for seven subjects, in a closed, supervised laboratory environment and use optical motion tracking system measurements as reference. As expected from an adaptive solution, the Kalman filter gives more stable results. The root mean square errors per pedalling cycle are below 3.2°, for both trials and for all subjects, implying that inertial measurement units are not only reliable for short measurements, as is usually assumed, but can be reliably used for longer measurements as well. Considering the accuracy of the results, the presented method can be reasonably extended to open, unsupervised environments and other joint angles. Implementing the presented method supports the development of cheaper and more efficient monitoring equipment, as opposed to using expensive motion tracking systems. Consequently, cyclists can have an affordable way of position tracking, leading to not only better bicycle fitting, but to the avoidance and prevention of certain injuries as well.

Descriptions of the dynamic joint space of the temporomandibular joint

BackgroundClinical diagnosis and treatment depended heavily on the motion analysis of the human joints. Although the dynamic joint space (DJS) of other organs was widely used in academic investigations, they were not universally used in the temporomandibular joint (TMJ) field, which was also important for the motion evaluation of the TMJ. The objectives of this study are to introduce the DJS of the TMJ and characterize the DJS regulars of mandibular movements. MethodsTen asymptomatic subjects were selected to instruct this application. The mouth opening and closing, mandibular protrusion, and left and right protrusions, were tracked by the optical motion tracking system. According to trajectories of markers and reconstructed models from computed tomography, the motions of the mandibles could be obtained. The DJSes, which were described as the minimum Euclidian distances, were subsequently calculated based on the geometrical surfaces between the condyle and fossa during the motions. Then, the DJS map could be drawn based on the calculated values. ResultsThe DJS map manifested a decreasing trend when the condyle crossed the glenoid fossa, while it generally increased after the condyle crossed the fossa during the mouth opening. The results showed that the average maximum and minimum anterior joint spaces were 5.39 mm and 2.07 mm during mouth opening respectively with a great discrepancy existing among the subjects. The average maximum and minimum anterior joint spaces were 4.74 mm and 2.19 mm during mandibular protrusion. As for left and right protrusions, the DJS of the contralateral side was greater than that of the ipsilateral side. ConclusionIn comparison to morphological analyses or only mandibular motions, the DJS provides more dynamic and interactive information about the TMJ. The research and methodology may help us comprehend TMJ motions and temporomandibular disorders.

Vertical Jump Data from Inertial and Optical Motion Tracking Systems

Motion capture (MOCAP) is a widely used technique to record human, animal, and object movement for various applications such as animation, biomechanical assessment, and control systems. Different systems have been proposed based on diverse technologies, such as visible light cameras, infrared cameras with passive or active markers, inertial systems, or goniometer-based systems. Each system has pros and cons that make it usable in different scenarios. This paper presents a dataset that combines Optical Motion and Inertial Systems, capturing a well-known sports movement as the vertical jump. As a reference system, the optical motion capture consists of six Flex 3 Optitrack cameras with 100 FPS. On the other hand, we developed an inertial system consisting of seven custom-made devices based on the IMU MPU-9250, which includes a three-axis magnetometer, accelerometer and gyroscope, and an embedded Digital Motion Processor (DMP) attached to a microcontroller mounted on a Teensy 3.2 with an ARM Cortex-M4 processor with wireless operation using Bluetooth. The purpose of taking IMU data with a low-cost and customized system is the deployment of applications that can be performed with similar hardware and can be adjusted to different areas. The developed measurement system is flexible, and the acquisition format and enclosure can be customized. The proposed dataset comprises eight jumps recorded from four healthy humans using both systems. Experimental results on the dataset show two usage examples for measuring joint angles and COM position. The proposed dataset is publicly available online and can be used in comparative algorithms, biomechanical studies, skeleton reconstruction, sensor fusion techniques, or machine learning models.

The effect of axillary crutch length on upper limb kinematics during swing-through gait.

Axillary crutches are commonly used in rehabilitation. Inappropriately fit crutches may result in upper limb pain or injury. To investigate the effects of axillary crutch length on upper limb kinematics to better understand potential injury mechanisms. It was hypothesized that crutches that were longer or shorter than standard-fit crutches would alter upper limb kinematics. Cross-sectional. Gait laboratory. Fifteen healthy males with no prior crutch experience. Participants were fit with axillary crutches using standardized methods, as well as with crutches that were 5 cm longer and 5 cm shorter. Participants performed swing-through gait (1.20 ± 0.07 ms-1 ) with all crutch lengths in randomized order. Kinematics were recorded using an optical motion-tracking system and joint angles for the scapula, shoulder, elbow, and wrist were computed. The effects of crutch length on joint range of motion (ROM) and joint angles at initial crutch contact were analyzed using multivariate analysis (Hotelling's T2 ; α=.025) and simultaneous confidence intervals (CI). The long-standard crutch fit comparison showed effects across all joints (ROM p=.009; initial contact p < .001). Longer crutches resulted in greater scapular upward rotation (mean difference [95% CI] ROM: 1.0 [-0.2 to 2.2]; initial contact: -2.7 [-4.4, -1.1]) and shoulder abduction (ROM: 0.8 [-0.1 to 1.8]; initial contact: -1.9 [-4.1 to 0.3]). Crutch length also had effects across all joints for the short-standard fit comparison (ROM p=.004; initial contact p=.016). Shorter crutches resulted in greater scapula downward rotation (2.2 [-0.4 to 4.8]) and greater shoulder adduction (2.5 [-0.6 to 5.6]) at initial contact. Shorter crutches also reduced shoulder flexion/extension ROM (-2.5 [-4.4 to -0.6]). Altered crutch length results in scapular and shoulder kinematic deviations that may present risk factors for upper limb injury with crutch-walking. This may underline the importance of appropriate device fitting to reduce injury risk in crutch users.

Vertical Jump Data From Inertial and Optical Motion Tracking System

Vertical Jump Data From Inertial and Optical Motion Tracking System

Multi-Inertial Sensor-Based Arm 3D Motion Tracking Using Elman Neural Network

Recent years have witnessed the rapid development of microelectromechanical systems, and human motion tracking technology based on IMU (inertial measurement unit) has attracted much attention. However, the magnetic field varies with time and position, which makes it necessary to calibrate sensors before tracking. To address the poor adaptability of IMU to the environments and improve the accuracy of estimated traces, this paper presents an ENN-based (Elman neural network) method to track human arm motions, which consists of two steps. First, the data derived from IMUs are preprocessed for the rough Euler angles; then, an ENN is trained to estimate motions. We explore the initially estimated position to calibrate the acceleration measurements as the input of the ENN. Real-world experiments of arm motion tracking are carried out with the ground truth from an optical motion tracking system. The experimental results show that the mean tracking errors are around 35 mm, with a strong ability to eliminate the effect of extreme measurement and environment noises, avoiding calibrating the magnetometer. The implementation of the well-trained model to independent motions indicates that the robustness of the proposed method is excellent, and the errors reduce by 37.2% on the x -axis and perform similarly on the z -axis compared with 4 traditional methods. This method quite suits those situations where trajectory tracking of the standardized motions is required, such as the medical habilitation.

Relationship between scapular control during isometric shoulder flexion and scapular motion during baseball pitching: a cross-sectional study

BackgroundA baseball pitcher with decreased scapular control may not be able to achieve suitable scapular motion at maximum shoulder external rotation (MER) of baseball pitching during the pitching action. It is common clinically to compare scapular control of the throwing and non-throwing arms to detect side-to-side differences. However, it remains unclear whether scapular control is different between the throwing and non-throwing arms. Moreover, no data exist on the relationship between scapular control and scapular motion at MER of pitching. Primarily, this study aimed to compare scapular control during isometric shoulder flexion between the throwing and non-throwing arms. Secondly, this study aimed to investigate the relationship between scapular control during isometric shoulder flexion and scapular motion at MER of pitching.MethodsFifteen healthy collegiate baseball pitchers (age, 20.2 ± 1.9 years; height, 1.76 ± 0.05 m; body mass, 73.3 ± 6.7 kg) were recruited. An optical motion tracking system was used to assess scapular motion. Scapular control was defined as the amount of change in the scapular internal rotation angle, downward rotation angle, and anterior tilt angle during isometric shoulder flexion. We assessed scapular position at MER of pitching.ResultsNo significant differences were detected for any of the scapular angles during isometric shoulder flexion between the throwing and non-throwing arms. The amount of change in the scapular internal rotation angle, scapular downward rotation angle, and scapular anterior tilt angle during isometric shoulder flexion had a significant relationship with the scapular downward rotation angle at MER.ConclusionsNo side-to-side difference was noted in scapular control during isometric shoulder flexion in healthy collegiate baseball pitchers at the group level. Further studies are required to understand the side-to-side differences at the individual level. Additionally, there was a relationship between scapular control during isometric shoulder flexion and scapular position at MER. These findings suggest that clinicians may consider using isometric shoulder flexion to assess scapular control in baseball pitchers.

Biomechanical Comparison of 2 Double Plating Methods in a Coronal Fracture Model of Bicondylar Tibial Plateau Fractures.

Because management of bicondylar tibial plateau fractures are complicated even for expert surgeons, with using a coronal fracture model, we aimed to compare 2 kinds of double locked plating techniques that consisted of the lateral locking plate and the medial locking plate inserted medial anteriorly (MA-ly) or medial posteriorly (MP-ly). Fourteen fresh-frozen tibias stabilized with the MA or MP methods were allocated into 2 groups with similar bone mineral density values. Implanted samples were tested under incremental fatigue loading conditions using a customized load applicator. An optical motion tracking system was used to assess relative displacements and rotations of fracture fragments during loading. Static and dynamic global stiffness, failure load, failure cycles, as well as movements of fracture fragments were measured. There were no significant differences between the 2 fixation methods regarding global stiffness, failure load, or failure cycles (P = 0.67-0.98, depending on the parameter). The kinematic evaluations, however, revealed that different positions of the medial locking plates altered the directions of movements for the medial-anterior or medial-posterior fracture segments. The mechanical stability of tibia-implant constructs fixed with the double plating methods was not remarkably affected by the location of the medial locking plate. Depending on clinical conditions and surgeons' preferences, bicondylar tibial plateau fractures can be managed with either MA or MP methods.

Optimizing a Feature-Based Motion Tracking System for Prospective Head Motion Estimation in MRI and PET/MRI

Patient head motion during magnetic resonance imaging (MRI) of the brain causes artifacts that limit diagnostic value. Prospective motion correction can, in principle, allow artifact-free imaging for any MRI sequence. Optical motion tracking systems are effective at measuring head motion for prospective motion correction but normally rely on attached markers, which are cumbersome and can move relative to the head. In this study, we optimized and benchmarked an optical motion tracking system that uses in-bore stereo-optical cameras to track feature patches on the forehead rather than attached markers. Feature patches were applied to the forehead in the form of an easily removable ink stamp or temporary tattoo. This approach has flexibility in camera positioning and allows tracking of a variety of surfaces on the human face, even those lacking prominent contours. This is advantageous given the limited space and line-of-sight with typical head coils. We optimized the accuracy and efficiency of two key components of the method: 1) the geometry of the stereo camera setup and 2) the feature detection and matching algorithm used for pose estimation. The absolute accuracy of the optimized feature-based method was compared with a commercial marker-based motion tracking system. Estimates of head motion of 15 volunteers simultaneously tracked by the two systems resulted in average positional discrepancies of less than 3 mm using a stamp and submillimeter average discrepancy using a feature-dense tattoo. These results suggest the feasibility of obtaining accurate head motion data for prospective motion compensated MRI using optimized feature-based motion tracking.

Geometric and dosimetric verification of a recurrent neural network algorithm to compensate for respiratory motion using an articulated robotic couch

The purpose of this study is to evaluate the performance of a recurrent neural network (RNN)-based prediction algorithm to compensate for respiratory movement using an articulated robotic couch system. A prototype of a real-time respiratory motion compensation couch was built using an optical 3D motion tracking system and a six-degree-of-freedom-articulated robotic system. To compensate for the system latency from motion detection to re-positioning of the system, RNN and double exponential smoothing (ES2) prediction algorithms were applied. Three aspects of performance were evaluated, simulation and experiments for geometric and dosimetric evaluations, using data from three liver and three lung patients who underwent stereotactic body radiotherapy. Overall, the RNN algorithm showed better geometric and dosimetric results than the other approaches. In simulation tests, RNN showed 82% average improvement ratio, compared with non-predicted results. In the geometric evaluation, RNN only showed average FWHM broadening of 1.5 mm, compared with the static case. In the dosimetric evaluation, RNN showed average gamma passing rates of 97.4 ± 1.0%, 89.0 ± 2.4% under the 3%/3 mm, 2%/2 mm respectively. It may be technically feasible to use the RNN prediction algorithm to compensate for respiratory motion with an articulated robotic couch system. The RNN algorithm could be widely used for motion compensation in patients undergoing radiotherapy.