Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network.

Objective. Speech decoding, one of the most intriguing brain-computer interface applications, opens up plentiful opportunities from rehabilitation of patients to direct and seamless communication between human species. Typical solutions rely on invasive recordings with a large number of distributed electrodes implanted through craniotomy. Here we explored the possibility of creating speech prosthesis in a minimally invasive setting with a small number of spatially segregated intracranial electrodes.Approach. We collected one hour of data (from two sessions) in two patients implanted with invasive electrodes. We then used only the contacts that pertained to a single stereotactic electroencephalographic (sEEG) shaft or an electrocorticographic (ECoG) stripe to decode neural activity into 26 words and one silence class. We employed a compact convolutional network-based architecture whose spatial and temporal filter weights allow for a physiologically plausible interpretation.Mainresults. We achieved on average 55% accuracy using only six channels of data recorded with a single minimally invasive sEEG electrode in the first patient and 70% accuracy using only eight channels of data recorded for a single ECoG strip in the second patient in classifying 26+1 overtly pronounced words. Our compact architecture did not require the use of pre-engineered features, learned fast and resulted in a stable, interpretable and physiologically meaningful decision rule successfully operating over a contiguous dataset collected during a different time interval than that used for training. Spatial characteristics of the pivotal neuronal populations corroborate with active and passive speech mapping results and exhibit the inverse space-frequency relationship characteristic of neural activity. Compared to other architectures our compact solution performed on par or better than those recently featured in neural speech decoding literature.Significance. We showcase the possibility of building a speech prosthesis with a small number of electrodes and based on a compact feature engineering free decoder derived from a small amount of training data.

Fast parametric curve matching (FPCM) for automatic spike detection.

Objective. Epilepsy is a widely spread neurological disease, whose treatment often requires resection of the pathological cortical tissue. Interictal spike analysis observed in the non-invasively collected EEG or MEG data offers an attractive way to localize epileptogenic cortical structures for surgery planning purposes. Interictal spike detection in lengthy multichannel data is a daunting task that is still often performed manually. This frequently limits such an analysis to a small portion of the data which renders the appropriate risks of missing the potentially epileptogenic region. While a plethora of automatic spike detection techniques have been developed each with its own assumptions and limitations, none of them is ideal and the best results are achieved when the output of several automatic spike detectors are combined. This is especially true in the low signal-to-noise ratio conditions. To this end we propose a novel biomimetic approach for automatic spike detection based on a constrained mixed spline machinery that we dub as fast parametric curve matching (FPCM).Approach. Using the peak-wave shape parametrization, the constrained parametric morphological model is constructed and convolved with the observed multichannel data to efficiently determine mixed spline parameters corresponding to each time-point in the dataset. Then the logical predicates that directly map to verbalized text-book like descriptions of the expected interictal event morphology allow us to accomplish the spike detection task.Main results. The results of simulations mimicking typical low SNR scenarios show the robustness and high receiver operating characteristic AUC values of the FPCM method as compared to the spike detection performed using more conventional approaches such as wavelet decomposition, template matching or simple amplitude thresholding. Applied to the real MEG and EEG data from the human patients and to rat ECoG data, the FPCM technique demonstrates reliable detection of the interictal events and localization of epileptogenic zones concordant with independent conclusions made by the epileptologist.Significance. Since the FPCM is computationally light, tolerant to high amplitude artifacts and flexible to accommodate verbalized descriptions of an arbitrary target morphology, it is likely to complement the existing arsenal of means for analysis of noisy interictal datasets.

The Combined Use of 5-ALA and Chlorin e6 Photosensitizers for Fluorescence-Guided Resection and Photodynamic Therapy under Neurophysiological Control for Recurrent Glioblastoma in the Functional Motor Area after Ineffective Use of 5-ALA: Preliminary Results.

The treatment of glial brain tumors is an unresolved problem in neurooncology, and all existing methods (tumor resection, chemotherapy, radiotherapy, radiosurgery, fluorescence diagnostics, photodynamic therapy, etc.) are directed toward increasing progression-free survival for patients. Fluorescence diagnostics and photodynamic therapy are promising methods for achieving gross total resection and additional treatment of residual parts of the tumor. However, sometimes the use of one photosensitizer for photodynamic therapy does not help, and the time until tumor relapse barely increases. This translational case report describes the preliminary results of the first combined use of 5-ALA and chlorin e6 photosensitizers for fluorescence-guided resection and photodynamic therapy of glioblastoma, which allowed us to perform total resection of tumor tissue according to magnetic resonance and computed tomography images, remove additional tissue with increased fluorescence intensity without neurophysiological consequences, and perform additional therapy. Two months after surgery, no recurrent tumor and no contrast uptake in the tumor bed were detected. Additionally, the patient had ischemic changes in the access zone and along the periphery and cystic-glial changes in the left parietal lobe.

Wavelet Ridges in EEG Diagnostic Features Extraction: Epilepsy Long-Time Monitoring and Rehabilitation after Traumatic Brain Injury.

Interchannel EEG synchronization, as well as its violation, is an important diagnostic sign of a number of diseases. In particular, during an epileptic seizure, such synchronization occurs starting from some pairs of channels up to many pairs in a generalized seizure. Additionally, for example, after traumatic brain injury, the destruction of interneuronal connections occurs, which leads to a violation of interchannel synchronization when performing motor or cognitive tests. Within the framework of a unified approach to the analysis of interchannel EEG synchronization using the ridges of wavelet spectra, two problems were solved. First, the segmentation of the initial data of long-term monitoring of scalp EEG with various artifacts into fragments suspicious of epileptic seizures in order to reduce the total duration of the fragments analyzed by the doctor. Second, assessments of recovery after rehabilitation of cognitive functions in patients with moderate traumatic brain injury. In the first task, the initial EEG was segmented into fragments in which at least two channels were synchronized, and by the adaptive threshold method into fragments with a high value of the EEG power spectral density. Overlapping in time synchronized fragments with fragments of high spectral power density was determined. As a result, the total duration of the fragments for analysis by the doctor was reduced by more than 60 times. In the second task, the network of phase-related EEG channels was determined during the cognitive test before and after rehabilitation. Calculation-logical and spatial-pattern cognitive tests were used. The positive dynamics of rehabilitation was determined during the initialization of interhemispheric connections and connections in the frontal cortex of the brain.

Decoding and interpreting cortical signals with a compact convolutional neural network.

Objective.Brain-computer interfaces (BCIs) decode information from neural activity and send it to external devices. The use of Deep Learning approaches for decoding allows for automatic feature engineering within the specific decoding task. Physiologically plausible interpretation of the network parameters ensures the robustness of the learned decision rules and opens the exciting opportunity for automatic knowledge discovery.Approach.We describe a compact convolutional network-based architecture for adaptive decoding of electrocorticographic (ECoG) data into finger kinematics. We also propose a novel theoretically justified approach to interpreting the spatial and temporal weights in the architectures that combine adaptation in both space and time. The obtained spatial and frequency patterns characterizing the neuronal populations pivotal to the specific decoding task can then be interpreted by fitting appropriate spatial and dynamical models.Main results.We first tested our solution using realistic Monte-Carlo simulations. Then, when applied to the ECoG data from Berlin BCI competition IV dataset, our architecture performed comparably to the competition winners without requiring explicit feature engineering. Using the proposed approach to the network weights interpretation we could unravel the spatial and the spectral patterns of the neuronal processes underlying the successful decoding of finger kinematics from an ECoG dataset. Finally we have also applied the entire pipeline to the analysis of a 32-channel EEG motor-imagery dataset and observed physiologically plausible patterns specific to the task.Significance.We described a compact and interpretable CNN architecture derived from the basic principles and encompassing the knowledge in the field of neural electrophysiology. For the first time in the context of such multibranch architectures with factorized spatial and temporal processing we presented theoretically justified weights interpretation rules. We verified our recipes using simulations and real data and demonstrated that the proposed solution offers a good decoder and a tool for investigating motor control neural mechanisms.

A Translational Study on Acute Traumatic Brain Injury: High Incidence of Epileptiform Activity on Human and Rat Electrocorticograms and Histological Correlates in Rats.

BACKGROUND: In humans, early pathological activity on invasive electrocorticograms (ECoGs) and its putative association with pathomorphology in the early period of traumatic brain injury (TBI) remains obscure. METHODS: We assessed pathological activity on scalp electroencephalograms (EEGs) and ECoGs in patients with acute TBI, early electrophysiological changes after lateral fluid percussion brain injury (FPI), and electrophysiological correlates of hippocampal damage (microgliosis and neuronal loss), a week after TBI in rats. RESULTS: Epileptiform activity on ECoGs was evident in 86% of patients during the acute period of TBI, ECoGs being more sensitive to epileptiform and periodic discharges. A "brush-like" ECoG pattern superimposed over rhythmic delta activity and periodic discharge was described for the first time in acute TBI. In rats, FPI increased high-amplitude spike incidence in the neocortex and, most expressed, in the ipsilateral hippocampus, induced hippocampal microgliosis and neuronal loss, ipsilateral dentate gyrus being most vulnerable, a week after TBI. Epileptiform spike incidence correlated with microglial cell density and neuronal loss in the ipsilateral hippocampus. CONCLUSION: Epileptiform activity is frequent in the acute period of TBI period and is associated with distant hippocampal damage on a microscopic level. This damage is probably involved in late consequences of TBI. The FPI model is suitable for exploring pathogenetic mechanisms of post-traumatic disorders.

Appliance of Navigated Transcranial Magnetic Stimulation in Radiosurgery for Brain Metastases.

PURPOSE: Navigated transcranial magnetic stimulation (nTMS) provides noninvasive visualization of eloquent brain areas. The nTMS is usually applied in presurgical planning to minimize the risk of surgery-related neurological deterioration. The aim of this study was to evaluate the usefulness of nTMS data for GammaKnife treatment planning for patients suffering from brain metastases. METHODS: Motor cortex mapping with nTMS was performed in eight patients with brain metastases within or adjacent to the precentral gyrus. The nTMS data set was imported into the planning software and fused with anatomical MRI. Then contouring of the target and critical structures was performed. Treatment plans with and without visualization of the functional structures by nTMS were analyzed and compared by neurosurgeon and medical physicist. RESULTS: The primary motor cortex was successfully delineated even in all cases despite significant peritumoral edema. Beam shaping and combined isocenters were used for conformal dose distribution and steeper dose fall-off near the identified eloquent zone. Compared with plans without nTMS data, treatment plans with integration of cortical nTMS mapping data showed a 2% to 78% (mean, 35.2% ± 22.7%) lower 12-Gy volume within the motor cortex without reduction of the dose applied to the tumor. CONCLUSIONS: The presented approach allows the easy and reliable integration of neurophysiological mapping data into GammaKnife treatment plans by the standard GammaPlan software. Diminishing the dose to critical structures might help to minimize side effects and therefore improve quality of life for brain metastasis patients.