Rizzoglio, F. | bioRxiv Science

bioRxiv2022

Monkey-to-human transfer of brain computer interface decoders

Intracortical brain-computer interfaces (iBCIs) enable paralyzed persons to generate movement, but current methods require large amounts of both neural and movement-related data to be collected from the iBCI user for supervised decoder training. We hypothesized that the low-dimensional latent neural representations of motor behavior, known to be preserved across time, might also be preserved across individuals, and allow us to circumvent this problem. We trained a decoder to predict the electromyographic (EMG) activity for a "source" monkey from the latent signals of motor cortex. We then used Canonical Correlation Analysis to align the latent signals of a "target" monkey to those of the source. These decoders were as accurate across monkeys as they were across sessions for a given monkey. Remarkably, the same process with latent signals from a human participant with tetraplegia was within 90% of the with-monkey decoding across session accuracy. Our findings suggest that consistent representations of motor activity exist across animals and even species. Discovering this common representation is a crucial first step in designing iBCI decoders that perform well without large amounts of data and supervised subject-specific tuning.

neuroscience↗

bioRxiv2022

Using adversarial networks to extend brain computer interface decoding accuracy over time

Existing intracortical brain computer interfaces (iBCIs) transform neural activity into control signals capable of restoring movement to persons with paralysis. However, the accuracy of the "decoder" at the heart of the iBCI typically degrades over time due to turnover of recorded neurons. To compensate, decoders can be recalibrated, but this requires the user to spend extra time and effort to provide the necessary data, then learn the new dynamics. As the recorded neurons change, one can think of the underlying movement intent signal being expressed in changing coordinates. If a mapping can be computed between the different coordinate systems, it may be possible to stabilize the original decoders mapping from brain to behavior without recalibration. We previously proposed a method based on Generalized Adversarial Networks (GANs), called "Adversarial Domain Adaptation Network" (ADAN), which aligns the distributions of latent signals within underlying low-dimensional neural manifolds. However, ADAN was tested on only a very limited dataset. Here we propose a method based on Cycle-Consistent Adversarial Networks (Cycle-GAN), which aligns the distributions of the full-dimensional neural recordings. We tested both Cycle-GAN and ADAN on data from multiple monkeys and behaviors and compared them to a linear method based on Procrustes Alignment of axes provided by Factor Analysis (PAF). Both GAN-based methods outperformed PAF. Cycle-GAN and ADAN (like PAF) are unsupervised and require little data, making them practical in real life. Overall, Cycle-GAN had the best performance and was easier to train and more robust than ADAN, making it ideal for stabilizing iBCI systems over time. Significance StatementThe inherent instabilities in the neural signals acquired by intracortical microelectrode arrays cause the performance of an intracortical brain computer interface (iBCI) decoder to drop over time, as the movement intent signal must essentially be recorded from neurons representing an ever-changing coordinate system. Here, we address this problem using Generative Adversarial Networks (GANs) to align these coordinates and compare their success to another, recently proposed linear method that uses Factor Analysis and Procrustes alignment. Our proposed methods are fully unsupervised, can be trained quickly, and require remarkably little new data. These methods should give iBCI users access to decoders with unchanging dynamics, and without the need for periodic supervised recalibration.

neuroscience↗