Chaofei Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chaofei Fan has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Jaimie M. Henderson
Department of Neurosurgery, Stanford University, Stanford, USA
5 shared publications - Leigh R. Hochberg
Massachusetts General Hospital
5 shared publications - Carrina Iacobacci
University of California, Davis
3 shared publications - David M. Brandman
University of California, Davis
3 shared publications - Francis R. Willett
Department of Neurosurgery, Stanford University, Stanford, CA, USA
3 shared publications - Maitreyee Wairagkar
University of California, Davis
3 shared publications
Latest Publications
- Open Access
Neural decoding of speech using deep neural ensembles
Speech brain-computer interfaces (BCIs) can restore rapid communication to people with paralysis, but decoding errors still limit performance. In recent brain-to-text decoding competitions, deep ensemble methods, which combine predictions from multiple independently trained decoders, have delivered striking accuracy improvements and account for the largest gains over baseline approaches. However, these methods have not previously been tested in real-time, require substantial computational resources, and their performance under various clinically relevant constraints remains poorly understood. Here, we present the first closed-loop test of deep ensembles in a participant with bilateral intracortical microelectrode arrays, demonstrating a reduction in word error rate from 33.7% to 26.0% on a large-vocabulary task. Using additional data from three participants, we then assess how these gains depend on baseline error rate, training dataset size, and ensemble size, including the resource-accuracy tradeoffs most relevant for real-world deployment. Finally, we introduce a computationally efficient pseudoensembling approach based on test-time augmentation that improves decoding accuracy while requiring only a single base decoder, greatly reducing the computational burden of ensembling. Together, these results show that the benefits of deep ensembling can be realized in real time and under practical resource constraints, bringing speech BCIs closer to broader clinical adoption.
Open AccessNeural decoding of speech using deep neural ensembles
Speech brain-computer interfaces (BCIs) can restore rapid communication to people with paralysis, but decoding errors still limit performance. In recent brain-to-text decoding competitions, deep ensemble methods, which combine predictions from multiple independently trained decoders, have delivered striking accuracy improvements and account for the largest gains over baseline approaches. However, these methods have not previously been tested in real-time, require substantial computational resources, and their performance under various clinically relevant constraints remains poorly understood. Here, we present the first closed-loop test of deep ensembles in a participant with bilateral intracortical microelectrode arrays, demonstrating a reduction in word error rate from 33.7% to 26.0% on a large-vocabulary task. Using additional data from three participants, we then assess how these gains depend on baseline error rate, training dataset size, and ensemble size, including the resource-accuracy tradeoffs most relevant for real-world deployment. Finally, we introduce a computationally efficient pseudoensembling approach based on test-time augmentation that improves decoding accuracy while requiring only a single base decoder, greatly reducing the computational burden of ensembling. Together, these results show that the benefits of deep ensembling can be realized in real time and under practical resource constraints, bringing speech BCIs closer to broader clinical adoption.
- Open Access
Error encoding in human speech motor cortex
Humans monitor their actions, including detecting errors during speech production. This self-monitoring capability also enables speech neuroprosthesis users to recognize mistakes in decoded output upon receiving visual or auditory feedback. However, it remains unknown whether neural activity related to error detection is present in the speech motor cortex. In this study, we demonstrate the existence of neural error signals in speech motor cortex firing rates during intracortical brain-to-text speech neuroprosthesis use. This activity could be decoded to enable the neuroprosthesis to identify its own errors with up to 86% accuracy. Additionally, we observed distinct neural patterns associated with specific types of mistakes, such as phonemic or semantic differences between the person’s intended and displayed words. These findings reveal how feedback errors are represented within the speech motor cortex, and suggest strategies for leveraging these additional cognitive signals to improve neuroprostheses.
Open AccessError encoding in human speech motor cortex
Humans monitor their actions, including detecting errors during speech production. This self-monitoring capability also enables speech neuroprosthesis users to recognize mistakes in decoded output upon receiving visual or auditory feedback. However, it remains unknown whether neural activity related to error detection is present in the speech motor cortex. In this study, we demonstrate the existence of neural error signals in speech motor cortex firing rates during intracortical brain-to-text speech neuroprosthesis use. This activity could be decoded to enable the neuroprosthesis to identify its own errors with up to 86% accuracy. Additionally, we observed distinct neural patterns associated with specific types of mistakes, such as phonemic or semantic differences between the person’s intended and displayed words. These findings reveal how feedback errors are represented within the speech motor cortex, and suggest strategies for leveraging these additional cognitive signals to improve neuroprostheses.
- Open Access
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/
Open AccessFew-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/
- Open Access
A flexible intracortical brain-computer interface for typing using finger movements
Keyboard typing with finger movements is a versatile digital interface for users with diverse skills, needs, and preferences. Currently, such an interface does not exist for people with paralysis. We developed an intracortical brain-computer interface (BCI) for typing with attempted flexion/extension movements of three finger groups on the right hand, or both hands, and demonstrated its flexibility in two dominant typing paradigms. The first paradigm is “point-and-click” typing, where a BCI user selects one key at a time using continuous real-time control, allowing selection of arbitrary sequences of symbols. During cued character selection with this paradigm, a human research participant with paralysis achieved 30-40 selections per minute with nearly 90% accuracy. The second paradigm is “keystroke” typing, where the BCI user selects each character by a discrete movement without real-time feedback, often giving a faster speed for natural language sentences. With 90 cued characters per minute, decoding attempted finger movements and correcting errors using a language model resulted in more than 90% accuracy. Notably, both paradigms matched the state-of-the-art for BCI performance and enabled further flexibility by the simultaneous selection of multiple characters as well as efficient decoder estimation across paradigms. Overall, the high-performance interface is a step towards the wider accessibility of BCI technology by addressing unmet user needs for flexibility.
Open AccessA flexible intracortical brain-computer interface for typing using finger movements
Keyboard typing with finger movements is a versatile digital interface for users with diverse skills, needs, and preferences. Currently, such an interface does not exist for people with paralysis. We developed an intracortical brain-computer interface (BCI) for typing with attempted flexion/extension movements of three finger groups on the right hand, or both hands, and demonstrated its flexibility in two dominant typing paradigms. The first paradigm is “point-and-click” typing, where a BCI user selects one key at a time using continuous real-time control, allowing selection of arbitrary sequences of symbols. During cued character selection with this paradigm, a human research participant with paralysis achieved 30-40 selections per minute with nearly 90% accuracy. The second paradigm is “keystroke” typing, where the BCI user selects each character by a discrete movement without real-time feedback, often giving a faster speed for natural language sentences. With 90 cued characters per minute, decoding attempted finger movements and correcting errors using a language model resulted in more than 90% accuracy. Notably, both paradigms matched the state-of-the-art for BCI performance and enabled further flexibility by the simultaneous selection of multiple characters as well as efficient decoder estimation across paradigms. Overall, the high-performance interface is a step towards the wider accessibility of BCI technology by addressing unmet user needs for flexibility.
- Open Access
An accurate and rapidly calibrating speech neuroprosthesis
Brain-computer interfaces can enable rapid, intuitive communication for people with paralysis by transforming the cortical activity associated with attempted speech into text on a computer screen. Despite recent advances, communication with brain-computer interfaces has been restricted by extensive training data requirements and inaccurate word output. A man in his 40’s with ALS with tetraparesis and severe dysarthria (ALSFRS-R = 23) was enrolled into the BrainGate2 clinical trial. He underwent surgical implantation of four microelectrode arrays into his left precentral gyrus, which recorded neural activity from 256 intracortical electrodes. We report a speech neuroprosthesis that decoded his neural activity as he attempted to speak in both prompted and unstructured conversational settings. Decoded words were displayed on a screen, then vocalized using text-to-speech software designed to sound like his pre-ALS voice. On the first day of system use, following 30 minutes of attempted speech training data, the neuroprosthesis achieved 99.6% accuracy with a 50-word vocabulary. On the second day, the size of the possible output vocabulary increased to 125,000 words, and, after 1.4 additional hours of training data, the neuroprosthesis achieved 90.2% accuracy. With further training data, the neuroprosthesis sustained 97.5% accuracy beyond eight months after surgical implantation. The participant has used the neuroprosthesis to communicate in self-paced conversations for over 248 hours. In an individual with ALS and severe dysarthria, an intracortical speech neuroprosthesis reached a level of performance suitable to restore naturalistic communication after a brief training period.
Open AccessAn accurate and rapidly calibrating speech neuroprosthesis
Brain-computer interfaces can enable rapid, intuitive communication for people with paralysis by transforming the cortical activity associated with attempted speech into text on a computer screen. Despite recent advances, communication with brain-computer interfaces has been restricted by extensive training data requirements and inaccurate word output. A man in his 40’s with ALS with tetraparesis and severe dysarthria (ALSFRS-R = 23) was enrolled into the BrainGate2 clinical trial. He underwent surgical implantation of four microelectrode arrays into his left precentral gyrus, which recorded neural activity from 256 intracortical electrodes. We report a speech neuroprosthesis that decoded his neural activity as he attempted to speak in both prompted and unstructured conversational settings. Decoded words were displayed on a screen, then vocalized using text-to-speech software designed to sound like his pre-ALS voice. On the first day of system use, following 30 minutes of attempted speech training data, the neuroprosthesis achieved 99.6% accuracy with a 50-word vocabulary. On the second day, the size of the possible output vocabulary increased to 125,000 words, and, after 1.4 additional hours of training data, the neuroprosthesis achieved 90.2% accuracy. With further training data, the neuroprosthesis sustained 97.5% accuracy beyond eight months after surgical implantation. The participant has used the neuroprosthesis to communicate in self-paced conversations for over 248 hours. In an individual with ALS and severe dysarthria, an intracortical speech neuroprosthesis reached a level of performance suitable to restore naturalistic communication after a brief training period.