Objective . Direct synthesis of speech from neural signals could provide a fast and natural way of communication to people with neurological diseases. Invasively-measured brain activity (electrocorticography; ECoG) supplies the necessary temporal and spatial resolution to decode fast and complex processes such as speech production. A number of impressive advances in speech decoding using neural signals have been achieved in recent years, but the complex dynamics are still not fully understood. However, it is unlikely that simple linear models can capture the relation between neural activity and continuous spoken speech. Approach . Here we show that deep neural networks can be used to map ECoG from speech production areas onto an intermediate representation of speech (logMel spectrogram). The proposed method uses a densely connected convolutional neural network topology which is well-suited to work with the small amount of data available from each participant. Main results . In a study with six participants, we achieved correlations up to r = 0.69 between the reconstructed and original logMel spectrograms. We transfered our prediction back into an audible waveform by applying a Wavenet vocoder. The vocoder was conditioned on logMel features that harnessed a much larger, pre-existing data corpus to provide the most natural acoustic output. Significance . To the best of our knowledge, this is the first time that high-quality speech has been reconstructed from neural recordings during speech production using deep neural networks.

Hydrocephalus is a common and costly neurological condition caused by the overproduction and/or impaired resorption of cerebrospinal fluid (CSF). The current standard of care, ventricular catheters (shunts), is prone to failure, which can result in nonspecific symptoms such as headaches, dizziness, and nausea. Current diagnostic tools for shunt failure such as computed tomography (CT), magnetic resonance imaging (MRI), radionuclide shunt patency studies (RSPSs), and ice pack–mediated thermodilution have disadvantages including high cost, poor accuracy, inconvenience, and safety concerns. Here, we developed and tested a noninvasive, skin-mounted, wearable measurement platform that incorporates arrays of thermal sensors and actuators for precise, continuous, or intermittent measurements of flow through subdermal shunts, without the drawbacks of other methods. Systematic theoretical and experimental benchtop studies demonstrate high performance across a range of practical operating conditions. Advanced electronics designs serve as the basis of a wireless embodiment for continuous monitoring based on rechargeable batteries and data transmission using Bluetooth protocols. Clinical studies involving five patients validate the sensor’s ability to detect the presence of CSF flow (P = 0.012) and further distinguish between baseline flow, diminished flow, and distal shunt failure. Last, we demonstrate processing algorithms to translate measured data into quantitative flow rate. The sensor designs, fabrication schemes, wireless architectures, and patient trials reported here represent an advance in hydrocephalus diagnostics with ability to visualize flow in a simple, user-friendly mode, accessible to the physician and patient alike.

Neuroplasticity is the ability of the brain to reorganize itself during normal development and in response to illness. Recent advances in neuroimaging and direct cortical stimulation in human subjects have given neuroscientists a window into the timing and functional anatomy of brain networks underlying this dynamic process. This review will discuss the current knowledge about the mechanisms underlying neuroplasticity, with a particular emphasis on reorganization following CNS pathology. First, traditional mechanisms of neuroplasticity, most relevant to learning and memory, will be addressed, followed by a review of adaptive mechanisms in response to pathology, particularly the recruitment of perilesional cortical regions and unmasking of latent connections. Next, we discuss the utility and limitations of various investigative techniques, such as direct electrocortical stimulation (DES), functional magnetic resonance imaging (fMRI), corticocortical evoked potential (CCEP), and diffusion tensor imaging (DTI). Finally, the clinical utility of these results will be highlighted as well as possible future studies aimed at better understanding of the plastic potential of the brain with the ultimate goal of improving quality of life for patients with neurologic injury.

In this data article, we provide the dataset which served as the basis for our related research article "Mapping critical cortical hubs and white matter pathways by direct electrical stimulation: an original functional atlas of the human brain" [1], which represents the first probabilistic cortical and subcortical atlas of critical structures mediating human brain functions based on direct electrical stimulation (DES) in patients undergoing awake brain surgery. 1162 cortical and 659 subcortical DES-derived responses were recorded during testing of 16 functional domains in 256 patients undergoing awake surgery. Normalized [Montreal Neurological Institute (MNI) 152] spatial coordinates for cortical and subcortical responses, and probabilistic heat maps for each functional domain, were computed using methods previously developed by our group [2,3]. Source data, including the MNI-normalized coordinates of all 1821 DES-derived cortical and subcortical data points, and multi-planar (MNI-152, T1 1mm) videos showing the probabilistic distribution of each functional domain are provided. This novel dataset can improve and refine our understanding about the functional anatomy of critical brain networks, and these data are made available for medical and neuroscience applications.

Glioblastoma multiforme (GBM) is a devastating disease without cure. It is also the most common primary brain tumor in adults. Although aggressive surgical resection is standard of care, these operations are limited by tumor infiltration of critical cortical and subcortical regions. A better understanding of how the brain can recover and reorganize function in response to GBM would provide valuable clinical data. This ability, termed neuroplasticity, is not well understood in the adult human brain. A better understanding of neuroplasticity in GBM could allow for improved extent of resection, even in areas classically thought to have critical, static function. The best evidence to date has demonstrated neuroplasticity only in slower growing tumors or through indirect measures such as functional MRI or transcranial magnetic stimulation. In this novel study, we utilize a unique experimental paradigm to show direct evidence of plasticity via serial direct electrocortical stimulation (DES) within primary motor (M1) and somatosensory (S1) cortices in GBM patients. Six patients with glioblastoma multiforme in or near the primary motor or somatosensory cortex were included in this retrospective observational study. These patients had two awake craniotomies with DES to map cortical motor and sensory sites in M1 and S1. Five of six patients exhibited at least one site of neuroplasticity within M1 or S1. Out of the 51 total sites stimulated, 32 (62.7%) demonstrated plasticity. Of these sites, 14 (43.7%) were in M1 and 18 (56.3%) were in S1. These data suggest that even in patients with GBM in or near primary brain regions, significant functional reorganization is possible. This is a new finding which may lead to a better understanding of the fundamental factors promoting or inhibiting plasticity. Further exploration may aid in treatment of patients with brain tumors and other neurologic disorders.