Targeted transcranial direct current stimulation combined with bimanual training for children with cerebral palsy

靶向经颅直流电刺激联合双手训练治疗脑瘫患儿

• 批准号: 10594264
• 负责人: Kathleen Margaret Friel
• 金额: $ 35.64万
• 依托单位: WINIFRED MASTERSON BURKE MED RES INST
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-26 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10594264
• 关键词: 3-Dimensional; Address; Adult; Architecture; Cerebral Palsy; Child; Clinical Research; Clinical Trials; Clinical assessments; Data; Data Set; Databases; Development; Enrollment; Ethics; Future; Goals; Gold; Hand; Hand functions; Image; Intervention; Machine Learning; Measures; Methods; Modeling; Motion; Movement; Movement Disorders; Participant; Pattern; Performance; Population; Publishing; Research; Research Personnel; Software Framework; Spastic Cerebral Palsy; System; Testing; Training; Underrepresented Populations; United States National Institutes of Health; Upper Extremity; Upper limb movement; base; cost; cost effective; data acquisition; data repository; deep learning; deep learning model; improved; kinematics; parent grant; repository; time use; tool; transfer learning

PROJECT SUMMARY The overall objective for the parent grant is to determine how to optimally target transcranial direct current stimulation (tDCS) to enhance the efficacy of upper extremity (UE) training in children with unilateral cerebral palsy (UCP). A key tool to determine whether this intervention leads to improves UE function is the use of clinical assessments. However, even the best assessments do not have the capacity to identify kinematic features of a child’s hand movement. Most assessments use time to complete a task as a corollary of hand function or subjective ratings of movement quality and function. By not capturing movement patterns using kinematics, there is a vital loss of information that could help optimize interventions. Existing methods of UE kinematics acquisition are not easily accessible because of their size, cost, and operational complexities. In this supplement proposal, we aim to use Deep Learning (DL) pose estimation models along with 3D depth sensing cameras to develop a cost effective, easy to use, and compact Deep Learning based markerless kinematic data acquisition (DL-KDA) system that can be applied to children with UCP. In order to achieve this overall goal, we must establish the accuracy and validity of the kinematic data obtained from the system. We will begin by developing a modular software framework for building and testing DL-KDA systems against a very precise marker-based motion capture gold standard (VICON). We will study the effects of 3D camera and DL parameters/architecture on the accuracy of the resulting kinematic data from healthy adult participants during BBT. Kinematic data from both, the DL-KDA and gold standard systems along with the respective DL-KDA parameter data will be transformed into an AI/ML ready HDF5 file. This will be published in public DL and NIH data repositories to encourage further development of ML applications using kinematic data. Once a validated and optimal DL-KDA configuration is identified, we will investigate this system’s suitability for applications to children with UCP. Since existing training datasets used for most DL pose estimation models are not inclusive of children and/or adults with movement disorders, potential ethical and scientific biases may arise if applied to an underrepresented group. To address this, we will use our large database of UCP assessment videos over the last 9 years to generate ~12,000 pose images of children with UCP. The Images will be transformed into ML/AI ready HDF5 datasets and published in public DL and NIH repositories. These datasets will be available for other researchers to consider when using or building DL pose estimation models for applications in UCP clinical research. We will use this dataset to perform transfer learning and retrain the optimal DL model previously identified. The performance of the retrained DL model will be statistically compared to the original DL model to verify if bias was indeed present. Finally, we will apply the optimal DL- KDA using the retrained model to ~20 children with UCP during the BBT. Validated kinematics for the UCP population, as well, will be uploaded to public DL and NIH repositories for use in future UCP research.

项目概要 母基金的总体目标是确定如何最佳地瞄准经颅直流电 刺激（tDCS）增强单侧脑瘫儿童上肢（UE）训练的效果 麻痹（UCP）。确定这种干预是否会改善 UE 功能的关键工具是使用 临床评估。然而，即使是最好的评估也无法识别运动学 孩子手部动作的特点。大多数评估都会使用时间来完成任务，作为手工的必然结果 功能或运动质量和功能的主观评价。通过不使用捕捉运动模式 运动学方面，有助于优化干预措施的信息严重丢失。 UE现有方法 由于其规模、成本和操作复杂性，运动学采集并不容易实现。 在此补充提案中，我们的目标是使用深度学习 (DL) 姿态估计模型以及 3D 深度传感相机，用于开发具有成本效益、易于使用且紧凑的基于深度学习的相机 可应用于UCP儿童的无标记运动数据采集（DL-KDA）系统。为了 为了实现这一总体目标，我们必须建立从运动学数据获得的准确性和有效性 系统。我们将首先开发一个用于构建和测试 DL-KDA 系统的模块化软件框架 反对非常精确的基于标记的动作捕捉黄金标准（VICON）。我们将研究3D的效果 相机和深度学习参数/架构对健康成人运动学数据准确性的影响 BBT 期间的参与者。来自 DL-KDA 和金标准系统以及 相应的 DL-KDA 参数数据将转换为 AI/ML 就绪的 HDF5 文件。这将发表在 公共 DL 和 NIH 数据存储库，鼓励使用运动学数据进一步开发 ML 应用程序。 一旦确定了经过验证的最佳 DL-KDA 配置，我们将调查该系统的适用性 对 UCP 儿童的应用。由于现有的训练数据集用于大多数深度学习姿态估计模型 不包括患有运动障碍的儿童和/或成人，潜在的伦理和科学偏见可能 如果应用于代表性不足的群体，就会出现这种情况。为了解决这个问题，我们将使用我们的大型 UCP 数据库 过去 9 年的评估视频生成了约 12,000 张 UCP 儿童的姿势图像。图像 将转换为 ML/AI 就绪的 HDF5 数据集，并在公共 DL 和 NIH 存储库中发布。这些 其他研究人员在使用或构建 DL 姿态估计模型时可以考虑使用数据集 用于 UCP 临床研究的应用。我们将使用该数据集来执行迁移学习并重新训练 先前确定的最佳深度学习模型。重新训练的深度学习模型的性能将被统计 与原始深度学习模型进行比较，以验证偏差是否确实存在。最后，我们将应用最优的 DL- KDA 在 BBT 期间对约 20 名 UCP 儿童使用重新训练的模型。经过验证的 UCP 运动学 人口也将上传到公共 DL 和 NIH 存储库，以用于未来的 UCP 研究。