Department of Neuroscience, Columbia University Medical Center, New York, New York.
Zuckerman Institute, Columbia University, New York, New York.
J Neurosci. 2022 Jan 12;42(2):220-239. doi: 10.1523/JNEUROSCI.2687-20.2021. Epub 2021 Oct 29.
Brain-machine interfaces (BMIs) for reaching have enjoyed continued performance improvements, yet there remains significant need for BMIs that control other movement classes. Recent scientific findings suggest that the intrinsic covariance structure of neural activity depends strongly on movement class, potentially necessitating different decode algorithms across classes. To address this possibility, we developed a self-motion BMI based on cortical activity as monkeys cycled a hand-held pedal to progress along a virtual track. Unlike during reaching, we found no high-variance dimensions that directly correlated with to-be-decoded variables. This was due to no neurons having consistent correlations between their responses and kinematic variables. Yet we could decode a single variable-self-motion-by nonlinearly leveraging structure that spanned multiple high-variance neural dimensions. Resulting online BMI-control success rates approached those during manual control. These findings make two broad points regarding how to build decode algorithms that harmonize with the empirical structure of neural activity in motor cortex. First, even when decoding from the same cortical region (e.g., arm-related motor cortex), different movement classes may need to employ very different strategies. Although correlations between neural activity and hand velocity are prominent during reaching tasks, they are not a fundamental property of motor cortex and cannot be counted on to be present in general. Second, although one generally desires a low-dimensional readout, it can be beneficial to leverage a multidimensional high-variance subspace. Fully embracing this approach requires highly nonlinear approaches tailored to the task at hand, but can produce near-native levels of performance. Many brain-machine interface decoders have been constructed for controlling movements normally performed with the arm. Yet it is unclear how these will function beyond the reach-like scenarios where they were developed. Existing decoders implicitly assume that neural covariance structure, and correlations with to-be-decoded kinematic variables, will be largely preserved across tasks. We find that the correlation between neural activity and hand kinematics, a feature typically exploited when decoding reach-like movements, is essentially absent during another task performed with the arm: cycling through a virtual environment. Nevertheless, the use of a different strategy, one focused on leveraging the highest-variance neural signals, supported high performance real-time brain-machine interface control.
脑机接口（BMI）在实现方面不断取得进步，但仍需要能够控制其他运动类别的 BMI。最近的科学发现表明，神经活动的内在协方差结构强烈依赖于运动类别，这可能需要在不同类别中使用不同的解码算法。为了解决这个问题，我们开发了一种基于皮层活动的自我运动 BMI，当猴子手持踏板循环踩踏以沿着虚拟轨道前进时，该 BMI 可以控制猴子的运动。与进行伸手动作时不同，我们没有发现与待解码变量直接相关的高方差维度。这是因为没有神经元的反应与运动学变量之间存在一致的相关性。然而，我们可以通过利用跨越多个高方差神经维度的结构来解码单个变量——自我运动。由此产生的在线 BMI 控制成功率接近手动控制时的成功率。这些发现提出了关于如何构建与运动皮层神经活动的经验结构协调一致的解码算法的两个广泛观点。首先，即使从相同的皮层区域（例如，手臂相关的运动皮层）进行解码，不同的运动类别也可能需要采用非常不同的策略。尽管在伸手任务中，神经活动与手部速度之间的相关性很明显，但它们不是运动皮层的基本特征，不能指望它们普遍存在。其次，尽管人们通常希望得到一个低维的输出，但利用多维高方差子空间可能会有益。完全采用这种方法需要根据手头的任务定制高度非线性的方法，但可以产生接近原生的性能。已经为控制通常用手臂进行的运动构建了许多脑机接口解码器。然而，尚不清楚这些解码器在它们开发的伸手类似场景之外将如何发挥作用。现有的解码器隐含地假设，神经协方差结构以及与待解码运动学变量的相关性，将在很大程度上保持跨任务不变。我们发现，在执行另一个使用手臂的任务（即循环穿越虚拟环境）时，神经活动与手部运动学之间的相关性，即通常用于解码伸手类似运动的特征，基本上不存在。然而，使用不同的策略，即专注于利用最高方差的神经信号，支持了高性能实时脑机接口控制。
