Suppr超能文献

使用自我中心视频在家中捕获脊髓损伤个体的手部使用:一项可行性研究。

Capturing hand use of individuals with spinal cord injury at home using egocentric video: a feasibility study.

机构信息

Institute of Biomedical Engineering, University of Toronto, Toronto, ON, Canada.

KITE, Toronto Rehabilitation Institute, University Health Network, Toronto, ON, Canada.

出版信息

Spinal Cord Ser Cases. 2021 Mar 5;7(1):17. doi: 10.1038/s41394-021-00382-w.

Abstract

STUDY DESIGN

Feasibility study.

OBJECTIVE

The objective of this study is to explore the feasibility of capturing egocentric (first person) video recordings in the home of individuals with cervical spinal cord injury (SCI) for hand function evaluation.

SETTING

Community-based study in Toronto, Ontario, Canada.

METHODS

Three participants with SCI recorded activities of daily living (ADLs) at home without the presence of a researcher. Information regarding recording characteristics and compliance was obtained as well as structured and semi-structured interviews involving privacy, usefulness, and usability. A video processing algorithm capable of detecting interactions between the hand and objects was applied to the home recordings.

RESULTS

In all, 98.58 ± 1.05% of the obtained footage was usable and included four to eight unique activities over a span of 3-7 days. The interaction detection algorithm yielded an F1 score of 0.75 ± 0.15.

CONCLUSIONS

Capturing ADLs using an egocentric camera in the home environment after SCI is feasible. Considerations regarding privacy, ease of use of the devices, and scheduling of recordings are provided.

摘要

研究设计

可行性研究。

目的

本研究旨在探索在颈脊髓损伤(SCI)患者家中采集自我中心(第一人称)视频记录以进行手部功能评估的可行性。

设置

加拿大安大略省多伦多市的基于社区的研究。

方法

3 名 SCI 患者在家中在没有研究人员在场的情况下记录日常生活活动(ADL)。获得有关记录特征和依从性的信息,并进行了涉及隐私、有用性和可用性的结构化和半结构化访谈。应用一种能够检测手与物体之间相互作用的视频处理算法,对家庭记录进行处理。

结果

总共,获得的可用视频片段的 98.58±1.05%,包括 3-7 天内四个至八个独特的活动。交互检测算法的 F1 得分为 0.75±0.15。

结论

在 SCI 后使用自我中心摄像机在家中环境中捕获 ADL 是可行的。提供了有关隐私、设备易用性和记录安排的注意事项。

相似文献

5
Automated Hand Prehension Assessment From Egocentric Video After Spinal Cord Injury.脊髓损伤后基于自我中心视频的自动手部抓握评估。
IEEE Trans Neural Syst Rehabil Eng. 2024;32:2864-2872. doi: 10.1109/TNSRE.2024.3438436. Epub 2024 Aug 12.
10
Tenodesis Grasp Detection in Egocentric Video.基于自我中心视频的经皮穿刺把持检测
IEEE J Biomed Health Inform. 2021 May;25(5):1463-1470. doi: 10.1109/JBHI.2020.3003643. Epub 2021 May 11.

本文引用的文献

8
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.更快的 R-CNN:基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验