Automated Hand Prehension Assessment From Egocentric Video After Spinal Cord Injury.

Hand function assessments in a clinical setting are critical for upper limb rehabilitation after spinal cord injury (SCI) but may not accurately reflect performance in an individual's home environment. When paired with computer vision models, egocentric videos from wearable cameras provide an opportunity for remote hand function assessment during real activities of daily living (ADLs). This study demonstrates the use of computer vision models to predict clinical hand function assessment scores from egocentric video. SlowFast, MViT, and MaskFeat models were trained and validated on a custom SCI dataset, which contained a variety of ADLs carried out in a simulated home environment. The dataset was annotated with clinical hand function assessment scores using an adapted scale applicable to a wide range of object interactions. An accuracy of 0.551±0.139, mean absolute error (MAE) of 0.517±0.184, and F1 score of 0.547±0.151 was achieved on the 5-class classification task. An accuracy of 0.724±0.135, MAE of 0.290±0.140, and F1 score of 0.733±0.144 was achieved on a consolidated 3-class classification task. This novel approach, for the first time, demonstrates the prediction of hand function assessment scores from egocentric video after SCI.

Elastic Biomaterial Scaffold with Spatially Varying Adhesive Design.

In order to secure biomaterials to tissue surfaces, sutures or glues are commonly used. Of interest is the development of a biomaterial patch for applications in tissue engineering and regeneration that incorporates an adhesive component to simplify patch application and ensure sufficient adhesion. A separate region dedicated to fulfilling the specific requirements of an application such as mechanical support or tissue delivery is also desirable. Here, the design and fabrication of a unique patch are presented with distinct regions for adhesion and function, resulting in a biomaterial patch resembling the Band-Aid. The adhesive region contains a novel polymer, synthesized to incorporate a molecule capable of adhesion to tissue, dopamine. The desired polymer composition for patch development is selected based on chemical assessment and evaluation of key physical properties such as swelling and elastic modulus, which are tailored for use in soft tissue applications. The selected polymer formulation, referred to as the adhesive patch (AP) polymer, demonstrates negligible cytotoxicity and improves adhesive capability to rat cardiac tissue compared to currently used patch materials. Finally, the AP polymer is used in the patch, designed to possess distinct adhesive and nonadhesive domains, presenting a novel design for the next generation of biomaterials.