Monkey-to-human transfer of trained iBCI decoders through nonlinear alignment of neural population dynamics

通过神经群体动态的非线性对齐，将经过训练的 iBCI 解码器从猴子转移到人类

• 批准号: 10791477
• 负责人: Lee Miller
• 金额: $ 44万
• 依托单位: NORTHWESTERN UNIVERSITY AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-06 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10791477
• 关键词: Address; Adopted; Algorithms; Architecture; Behavior; Binding; Biomimetics; Brain; Chicago; Collaborations; Complex; Computer Vision Systems; Consent; Data; Dimensions; Hand; Human; Image; Learning; Life; Limb structure; Literature; Machine Learning; Maps; Methods; Monkeys; Motor Cortex; Motor output; Movement; Muscle; Neurofibrillary Tangles; Neurons; Output; Paralysed; Persons; Population Dynamics; Positioning Attribute; Procedures; Process; Psychological Transfer; Quadriplegia; Recurrence; Reporting; Robotics; Sampling; Signal Transduction; Source; Spinal cord injury; Stereotyping; Structure; System; Techniques; Testing; Time; Training; Translating; Universities; User-Computer Interface; Work; Wrist; analytical tool; arm movement; brain computer interface; brain surgery; design; functional electrical stimulation; generative adversarial network; improved; joint stiffness; kinematics; loss of function; motor behavior; neglect; network architecture; neural; novel; novel strategies; preservation; tool; transfer learning; wireless

Project Summary Nearly 80% of persons with quadriplegia would consent to brain surgery to regain some use of their hands. Yet, despite advances made in the past 15 years, Intracortical Brain-Computer Interfaces (iBCIs) remain largely limited to controlling only the kinematics of simple robotic hand movements. Furthermore, decoder training data consists of a trajectory the user observes and attempts to imitate, together with the accompanying neural activity. But this “observation-based” decoding is not feasible for iBCIs that decode force or muscle activity (EMG), signals which will be needed for more nearly biomimetic iBCIs controlling contact forces and joint stiffness. We now propose a radical new approach, based on machine learning techniques used in the artificial vison and image manipulation fields, to “transfer” a decoder computed from data collected from a monkey to a human with a paralyzed hand. The key to the approach is the observation that the neural activity accompanying movement lies largely on a low-dimensional manifold within the neural state space of recorded neurons. The “latent signals” within the manifold bear remarkably stable information about behavior that is potentially useful for iBCIs. However, any given sample of neurons embeds the manifold in a different coordinate system. We have previously used Canonical Correlation Analysis (CCA) to realign these manifolds for stereotypic, trial- based tasks. We used a fixed BCI decoder with CCA-aligned latent-signal inputs to predict arm movement for as long as two years (“cross-time alignment”). Similarly, we made EMG predictions from a monkey using a decoder computed for a different monkey (“cross-subject alignment”), and even from M1 signals recorded from a person with a spinal cord injury (“cross-species alignment”). But CCA can work only on behaviors that can be trial-aligned, which is not possible for most movements typical of a person's daily life. Here, we propose to develop a new class of tools based on cycle-GAN, a Generative Adversarial Network. Because cycle-GAN works by minimizing the distance between point clouds within the manifold, it can be applied to unconstrained movements. In our initial tests, Cycle-GAN outperformed CCA when used for cross-time alignment of simple behaviors, but it failed for unconstrained behaviors and cross-subject alignment. We propose to optimize cycle- GAN by incorporating information about dynamics (Aim 1), and by initially constraining the particular regions of two partially overlapping manifolds that we subject to the alignment process (Aim 2). We will develop and validate these methods on data recorded during stereotypical motor behaviors in the lab, on unconstrained data collected wirelessly from monkeys housed in a large, plastic cage, and from humans with spinal cord injury through an on- going collaboration with groups at the Universities of Pittsburgh and Chicago. The final result will be a set of novel analytical tools that can be used both to understand the brain's representation of complex motor behaviors, and to develop applications to a new class of more broadly applicable iBCIs.

项目摘要 近80％的四肢瘫痪患者同意脑外科手术以保持某种手术。然而， 尽管在过去的15年中取得了进展 仅限于仅控制简单机器人手动运动的运动学。此外，解码器培训数据 由用户观察和试图模仿参与神经活动的轨迹组成。 但是，对于解码力或肌肉活动（EMG）的IBCI，这种“基于观察的”解码是不可行的 需要更多接触力和关节刚度的几乎仿生IBCI所需的。我们现在 提出一种基于人工粘膜中使用的机器学习技术的根本新方法 图像操纵字段，以“转移”从猴子收集到人类的数据计算的解码器 用瘫痪的手。方法的关键是观察到涉及的神经活动 运动主要位于记录神经元的神经元空间内的低维歧管。 多种多样的熊内的“潜在信号”有关行为的明显稳定信息可能是潜在的 对IBCIS有用。但是，任何给定的神经元样品都将歧管嵌入不同的坐标系中。 我们以前已经使用规范相关分析（CCA）来重新调整这些歧管，以进行刻板印象，试验 基于任务。我们使用固定的BCI解码器与CCA对准潜在信号输入来预测手臂运动 长达两年（“跨时间对齐”）。同样，我们使用猴子从猴子做出了EMG预测 计算出针对不同猴子的解码器（“交叉对象对齐”），甚至是根据从记录的M1信号中 脊髓损伤的人（“跨物种对齐”）。但是CCA只能在可以的行为上工作 经过试验，这对于一个人的日常生活中典型的大多数运动都是不可能的。在这里，我们建议 基于Cycle-Gan开发新的工具，该工具是一种生成的对抗网络。因为自行车有效 通过最小化歧管内点云之间的距离，可以将其应用于无约束的 动作。在我们的初始测试中，当使用简单的交叉时间对齐时，自行车的表现优于CCA 行为，但由于不受约束的行为和跨主题对齐方式失败了。我们建议优化循环 - 通过合并有关动态的信息（AIM 1），并最初限制 我们遵守对齐过程的两个部分重叠的歧管（AIM 2）。我们将开发和验证 这些方法是在实验室中刻板印象的电动机行为期间记录的数据，收集的无约束数据 无线从猴子中无线塑料笼中，以及通过脊髓损伤的人通过 - 与匹兹堡大学和芝加哥大学合作。最终结果将是一组 可以用来了解大脑对复杂运动行为的表示的新型分析工具， 并为新的更广泛适用的IBCIS开发应用程序。