24 January 2022 in Journal of NeuroEngineering and Rehabilitation
Background: Mirror therapy (MT) has been used for functional recovery of the affected hand by providing the mirrored image of the unaffected hand movement, which induces neural activation of the cortical hemisphere contralateral to the affected hand. Recently, many wearable robots assisting the movement of the hand have been developed, and several studies have proposed robotic mirror therapy (RMT) that uses a robot to provide mirrored movements of the unaffected hand to the affected hand with the robot controlled by measuring electromyography or posture of the unaffected hand. In some cases of RMT a mirror is placed to allow the person to observe only the unaffected hand but in others users simply observe the robotically assisted hand performing the mirrored movements, as was the case in this study. There have been limited evaluations of the cortical activity during RMT compared to MT and robotic therapy (RT) providing passive movements despite the difference in the modality of sensory feedback and the involvement of motor intention, respectively. Methods: This paper analyzes bilateral motor cortex activation in nine healthy subjects and five chronic stroke survivors during a pinching task performed in MT, RT, and RMT conditions using functional near infrared spectroscopy (fNIRS). In the MT condition, the person moved the unaffected hand and observed it in a mirror while the affected hand remained still. In RT condition passive movements were provided to the affected hand with a cable-driven soft robotic glove, while, in RMT condition, the posture of the unaffected hand was measured by a sensing glove and the soft robotic glove mirrored its movement on the affected hand. Results: For both groups, the RMT condition showed the greatest mean cortical activation on the motor cortex contralateral to the affected (non-dominant for the healthy group) hand compared to other conditions. Individual results indicate that RMT induces similar or greater neural activation on the motor cortex compared to MT and RT conditions. The interhemispheric activations of both groups were balanced in RMT condition. In MT condition, significantly greater activation was shown on the hemisphere ipsilateral to the affected (dominant for the healthy group) hand for both subject groups, while the contralateral side showed significantly greater activation for the healthy group in RT condition. Conclusion: The experimental results indicate that combining visual feedback, somatosensory feedback, and motor intention are important for greater stimulation on the contralateral motor cortex of the affected hand. RMT that includes these factors is hypothesized to achieve a more effective functional rehabilitation due to greater and more balanced cortical activation.
12 January 2024 in IEEE Transactions on Industrial Informatics
For stroke survivors, diminished hand functions limit their ability to perform activities of daily living (ADLs). Recently, soft-robotic gloves have assisted stroke survivors in active rehabilitation by facilitating their finger movements based on intentions expressed through biosignals, such as electromyogram and electroencephalogram. In this regard, helping stroke survivors actively train multiple hand postures can improve hand functions required for ADLs. However, detecting intentions regarding multiple hand postures remains challenging, often resulting in low online classification performance. To address this, we propose a hand rehabilitation system comprising a vision-based intention detection framework and 8-degree-of-freedom soft-robotic glove. Our proposed framework, depth enhanced hand posture intention network, analyzes images and depths data observing users' arm behavior and hand-object interactions to predict intentions for multiple hand postures. The 8-degrees-of-freedom soft-robotic glove facilitates flexion and extension of individual fingers to help users perform desired hand postures. To support active rehabilitation, we operate our glove to facilitate user's finger movements when the user exerts effort to generate desired hand postures. We test our system on a real-time pick and place task involving five hand postures most commonly utilized in ADLs. Our vision-based system could predict and facilitate the desired hand postures for five healthy individuals and three stroke survivors with average accuracy of 90.4 ± 3.6% and 80.3 ± 4.6%, respectively, outperforming methods reported in previous studies.
20 April 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Gait impairment represented by crouch gait is the main cause of decreases in the quality of lives of children with cerebral palsy. Various robotic rehabilitation interventions have been used to improve gait abnormalities in the sagittal plane of children with cerebral palsy, such as excessive flexion in the hip and knee joints, yet in few studies have postural improvements in the coronal plane been observed. The aim of this study was to design and validate a gait rehabilitation system using a new cable-driven mechanism applying assist in the coronal plane. We developed a mobile cable-tensioning platform that can control the magnitude and direction of the tension vector applied at the knee joints during treadmill walking, while minimizing the inertia of the worn part of the device for less obstructing the natural movement of the lower limbs. To validate the effectiveness of the proposed system, three different treadmill walking conditions were performed by four children with cerebral palsy. The experimental results showed that the system reduced hip adduction angle by an average of 4.57 ± 1.79° compared to unassisted walking. Importantly, we also observed improvements of hip joint kinematics in the sagittal plane, indicating that crouch gait can be improved by postural correction in the coronal plane. The device also improved anterior and lateral pelvic tilts during treadmill walking. The proposed cable-tensioning platform can be used as a rehabilitation system for crouch gait, and more specifically, for correcting gait posture with minimal disturbance to the voluntary movement.
2 April 2026 in JMIR Preprints
BACKGROUND Accurate joint motion analysis in the sagittal, frontal, and transverse planes is critical for clinical assessments. While retroreflective-marker-based systems (e.g., VICON) have been the gold standard in motion analysis due to their high precision, their high cost and the requirement for expert setup limit their use outside laboratory environments. Markerless methods have emerged but often suffer from reduced accuracy, especially for non-sagittal joint motions in the limbs. OBJECTIVE This study proposes a single-camera-based motion capture system that utilizes printed visual patterns on compression tights paired with a low-cost RGBD camera to estimate three-dimensional joint angle trajectories during human dynamic motions. The primary objective is achieving clinically acceptable accuracy using a single camera to enable accurate joint kinematic analysis. METHODS The proposed system was demonstrated with a focus on the knee joint. For three-degree-of-freedom knee joint angle estimation, unstructured visual patterns were printed on the thigh and shank regions of lower-limb compression tights. The visual patterns were designed using specific initials but can be replaced with commercial logos or other graphic designs. The proposed algorithm independently tracks pose changes of the visual pattern regions on the thigh and shank to estimate knee joint kinematics. The algorithm consists of a pattern segmentation network (PSN) for extracting thigh and shank pattern images and an optical flow network (PON) optimized to track inter-frame pattern motion with sub-pixel accuracy. Using dense pixel-wise correspondences estimated by the PON, point clouds are reconstructed from depth images and registered across consecutive frames to estimate segment-wise pose changes, enabling continuous knee joint angle tracking. RESULTS Ten healthy participants were recruited for the experiment. Each participant wore compression tights printed with visual patterns and performed five repetitions of a single-leg squat. Knee joint angles were simultaneously measured using the proposed system and a VICON motion capture system, and the differences between the two measurements were analyzed. Experimental validation against the VICON as a reference system achieved root-mean-square errors of 2.2°, 1.4°, and 1.2° for flexion/extension, abduction/adduction, and rotation, respectively. CONCLUSIONS The proposed system achieved clinically acceptable accuracy and provides a practical solution for three-degree-of-freedom knee joint kinematics assessment without requiring extensive equipment or multi-camera setups. CLINICALTRIAL The experimental protocols were approved by the Institutional Review Board at the Korea Advanced Institute of Science and Technology (ICTRP Identifier KCT0011010, URL: https://trialsearch.who.int/Trial2.aspx?TrialID=KCT0011010)
23 September 2026 in Advanced Healthcare Materials
Effective musculoskeletal rehabilitation requires simultaneous assessment of muscle activation and movement kinematics, yet no current system enables this at home. Laboratory motion capture systems provide accurate kinematics but require controlled environments, while portable inertial sensors enable home use at the cost of drift and incomplete joint angle resolution. Critically, neither approach provides direct physiological insight into the muscle activation driving functional movement. Here, we present NeuroVisio SyncPatch, a wearable multimodal platform that unifies conformal surface electromyography (EMG) with vision‐based motion tracking within a single sports–tape interface. The device integrates stretchable, breathable, electrically conductive adhesive (ECA) electrodes that enable stable EMG acquisition, along with printed optical markers supporting accurate 3‐degree‐of‐freedom (DOF) knee angle estimation utilizing a single RGB‐D camera per leg via a convolutional neural network (CNN)‐based vision pipeline. By integrating high‐fidelity EMG signals (SNR > 13 dB) with joint kinematics, the system delivered real‐time kinematic feedback during movement together with EMG‐derived neuromuscular feedback after each trial. Multimodal feedback training showed improved knee alignment and intermuscular coordination in participants with dynamic knee valgus (DKV), demonstrating closed‐loop modulation of maladaptive motor patterns. NeuroVisio SyncPatch establishes a scalable, mechanically robust, and physiologically comprehensive framework for home‐deployable musculoskeletal rehabilitation.