PostureCheck: A vision-based compensatory-posture-detection tool to enhance performance of the BURT® upper-extremity stroke-therapy device

项目总结/摘要 这个小企业创新研究（SBIR）第二阶段项目提出了部署一个AI驱动的 名为PostureCheck™的图像处理工具，可自动检测患者何时出现不良行为 机器人辅助上肢（UE）康复训练期间的代偿运动。该系统 基于标准摄像机和NIH第一阶段开发的人工智能（AI）软件， 项目PostureCheck™将与Barrett Technology现有的Burt® UE康复机器人完全集成， 确保向患者提供适当和及时的反馈，以鼓励正确执行 不需要治疗师持续监督的治疗练习。 Burt®是一款FDA上市的UE康复机器人，它可以支撑患者手臂和手部的重量， 患者移动他/她的手臂以与屏幕上的游戏交互。Burt®提供视觉和触觉引导协助 反馈、活动和评估，以帮助培训患者和衡量进展。临床研究 已经表明，Burt®可用于改善患者在与治疗师进行一对一治疗时的表现。 然而，该系统缺乏单个治疗师监测和与多个患者一起工作的能力， Burt®系统。 拟议的SBIR第二阶段活动分为三个目标。在目标1中，生成的注释数据集 在第一阶段，将用于开发三个独立的AI模块。这些模块将被纳入一个框架 允许治疗师监控模块的结果，并通过反馈，使系统能够自动 适应不断提高性能。在目标2中，将收集和综合利益攸关方的反馈， 为PostureCheck™工具设计多个用户界面。将创建特定的接口， 治疗师在RT疗程期间和之后。PostureCheck™将与Burt®设备集成， 治疗师向患者提供有效的反馈，并阻止使用代偿性运动。最后在 目标3：在一项采用PostureCheck™的干预性研究中招募42名卒中幸存者， Burt®系统。受试者将接受18次RT治疗，采用个体或分组治疗形式。电机 将比较各组之间的表现，以收集有关组合的适用性的信息。 用于未来康复中心的多患者RT治疗系统。 该项目的长期商业目标是提供实用的Burt®-plus-PostureCheck™系统， 使治疗师能够通过各种有用的功能同时监督多个患者。的 该系统将适合部署在诊所以及康复中心（例如健身房）。

Project Summary/Abstract This Small Business Innovation Research (SBIR) Phase-II project proposes the deployment of an AI-powered image-processing tool, named PostureCheck™, to automatically detect when patients perform undesirable compensatory movements during robot-assisted upper-extremity (UE) rehabilitation exercises. The system is based on a standard video camera and the artificial intelligence (AI) software developed under the NIH Phase-I project. PostureCheck™ will be fully integrated with Barrett Technology's existing Burt® UE rehabilitation robot, ensuring that patients are provided appropriate and timely feedback to encourage the correct performance of therapeutic exercises without requiring constant therapist supervision. Burt® is an FDA-listed UE rehabilitation robot that supports the weight of a patient's arm and hand while the patient moves his/her arm to interact with on-screen games. Burt® offers guided assistance, visual and haptic feedback, and activities and assessments to both help train the patient and measure progress. Clinical studies have shown that Burt® can be used to improve patients' performance in one-on-one sessions with a therapist. However, the system lacks the capability for a single therapist to monitor and work with several patients and Burt® systems at one time. The proposed SBIR Phase-II activities are organized in three aims. In Aim 1, the annotated dataset generated in Phase-I will be used to develop three separate AI modules. These modules will be integrated into a framework that allows therapists to monitor the outcome of the modules, and, through feedback, enable the system to auto- adapt to improve performance continuously. In Aim 2, stakeholder feedback will be gathered and integrated to design multiple user interfaces for the PostureCheck™ tool. Specific interfaces will be created for use by therapists during and after RT sessions. PostureCheck™ will be integrated with the Burt® device to empower therapists to provide effective feedback to patients and deter the use of compensatory movements. Finally, in Aim 3, forty-two stroke survivors will be recruited in an interventional study deploying the PostureCheck™ and Burt® systems. Subjects will undergo eighteen RT sessions in either an individual or group therapy format. Motor performance between groups will be compared to gather information about the suitability of the combined systems for multi-patient RT therapy in future rehabilitation centers. The long-term commercial goal of the project is to provide a practical Burt®-plus-PostureCheck™ system to empower therapists to supervise multiple patients simultaneously through a gamut of useful functionalities. The system will be suitable for deployment in clinics as well as rehabilitation centers such as wellness gyms.