A portable, self-contained neuroprosthetic hand with deep learning-based finger control
A portable, self-contained neuroprosthetic hand with deep learning-based finger control
复制标题
便携式、独立的神经假手，具有基于深度学习的手指控制
DOI：
10.1088/1741-2552/ac2a8d
复制
发表时间：
2021
影响因子：
4
通讯作者：
Yang, Zhi
中科院分区：
文献类型：
--
作者：
Nguyen, Anh Tuan;Drealan, Markus W;Khue Luu, Diu;Jiang, Ming;Xu, Jian;Cheng, Jonathan;Zhao, Qi;Keefer, Edward W;Yang, Zhi
Objective.基于深度学习的神经解码器已经成为实现神经假手灵巧和直观控制的主要方法。然而，由于其高计算要求，很少有研究将深度学习应用于临床环境。Approach.边缘计算设备的最新进展带来了缓解这一问题的潜力。在这里，我们提出了一个神经假肢手与嵌入式深度学习为基础的控制的实现。神经解码器基于递归神经网络架构设计，并部署在NVIDIA Jetson Nano上，这是一个紧凑而强大的边缘计算平台，用于深度学习推理。这使得神经假手能够作为便携式和独立的单元来实现，其具有对个体手指运动的实时控制。主要结果。对经桡动脉截肢者进行了一项初步研究，使用从植入的神经束内微电极获取的周围神经信号来评估所提出的系统。初步的实验结果表明，该系统的能力，提供强大的，高精度（95%-99%）和低延迟（50-120 ms）的控制个人手指运动在各种实验室和现实世界的环境。结论这项工作是现代边缘计算平台的技术演示，可以有效使用基于深度学习的神经解码器作为自主系统进行神经假体控制。意义所提出的系统有助于开创深度神经网络在临床应用中的部署，这些应用是一类具有嵌入式人工智能的新型可穿戴生物医学设备的基础。临床试验注册：通过神经束靶向进行的异常手控制（DEFT）。标识符：NCT02994160.Export引文和摘要BibTeX RIS
Objective. Deep learning-based neural decoders have emerged as the prominent approach to enable dexterous and intuitive control of neuroprosthetic hands. Yet few studies have materialized the use of deep learning in clinical settings due to its high computational requirements. Approach. Recent advancements of edge computing devices bring the potential to alleviate this problem. Here we present the implementation of a neuroprosthetic hand with embedded deep learning-based control. The neural decoder is designed based on the recurrent neural network architecture and deployed on the NVIDIA Jetson Nano—a compacted yet powerful edge computing platform for deep learning inference. This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements. Main results. A pilot study with a transradial amputee is conducted to evaluate the proposed system using peripheral nerve signals acquired from implanted intrafascicular microelectrodes. The preliminary experiment results show the system's capabilities of providing robust, high-accuracy (95%–99%) and low-latency (50–120 ms) control of individual finger movements in various laboratory and real-world environments. Conclusion. This work is a technological demonstration of modern edge computing platforms to enable the effective use of deep learning-based neural decoders for neuroprosthesis control as an autonomous system. Significance. The proposed system helps pioneer the deployment of deep neural networks in clinical applications underlying a new class of wearable biomedical devices with embedded artificial intelligence.Clinical trial registration: DExterous Hand Control Through Fascicular Targeting (DEFT). Identifier: NCT02994160.Export citation and abstract BibTeX RIS
登录
查看更多内容
影响因子：
1.5
作者：
Resnik, Linda;Klinger, Shana L.;Etter, Katherine
通讯作者：
Etter, Katherine
影响因子：
4
作者：
Anh Tuan Nguyen;Xu, Jian;Yang, Zhi
通讯作者：
Yang, Zhi
影响因子：
4
作者：
Overstreet, Cynthia K.;Cheng, Jonathan;Keefer, Edward W.
通讯作者：
Keefer, Edward W.
影响因子：
3.4
作者：
Brinton MR;Barcikowski E;Davis T;Paskett M;George JA;Clark GA
通讯作者：
Clark GA
影响因子：
4.6
作者：
E. Wolf;T. Cruz;A. Emondi;N. Langhals;Stephanie N. Naufel;G. Peng;Brian W. Schulz;Michael Wolfson
通讯作者：
Michael Wolfson