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.

To evaluate the results of surgical treatment of patients with pharmacoresistant epilepsy. Examination and surgical treatment of 61 patients with pharmacoresistant forms of symptomatic epilepsy were performed from 01.01.14 to 01.05.16. The results confirmed the safety and efficacy of the surgical treatment of pharmacoresistant epilepsy. After 12 months, seizures were controlled in 69% of operated patients. The necessity of complex examination of all patients with pharmacoresistant epilepsy to make a decision about possible surgery is shown.

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. Main results . 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.

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.

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.

Chronic disorders of consciousness (DOC) represent severe central nervous system damage resulting in long-term disability and a significant burden to healthcare institutions and patientsʼ families. DOC develop in patients after coma and are characterized by the presence of wakefulness with complete or almost complete absence of signs of awareness. DOC include vegetative state (VS) and minimally conscious state (MCS). The term prolonged disorders of consciousness (pDOC) is also used in the Russian literature to describe the initial stages of chronic DOC. Another clinical entity, exit from MCS, is used to characterize the stage of recovery of cognitive functions. Diagnosis of DOC is based on repeated structured clinical examination using specific scales, provided that reversible causes of impaired consciousness are excluded. Treatment of DOC patients includes maintenance of vital functions and optimal nutrition and control of typical complications and concomitant conditions (pressure sores, spasticity, pain, paroxysmal sympathetic hyperactivity, etc.). Rehabilitation of DOC patients should involve a multidisciplinary rehabilitation team, the extent of which is determined by the individual problems and capabilities of the patient. Rehabilitation is most effective if started early. To date, there is no robust evidence on the effectiveness of specific methods for restoring consciousness, while a number of pharmacological and non-pharmacological interventions are being studied; however, they should be applied provided that the maximum possible level of correction of the patientʼs somatic problems is achieved. The family plays a key role in rehabilitation. They need practical information about their loved oneʼs condition, guidance in rehabilitation, and psychological support. Хронические нарушения сознания (ХНС) представляют собой синдромы тяжелого поражения центральной нервной системы, приводящие к длительной грубой инвалидизации и требующие значительных усилий по лечению и реабилитации, которые ложатся на медицинские учреждения и на плечи близких пациентов. ХНС развиваются у пациентов после комы и характеризуются наличием бодрствования при полном или практически полном отсутствии признаков осознанного поведения. К ХНС относятся вегетативное состояние (ВС) и состояние минимального сознания (СМС). Также для описания начальных стадий этих состояний используется термин «продленное нарушение сознания» (ПНС). Отдельно выделяют выход из СМС — состояние, которое формируется по мере восстановления когнитивных функций. Диагностика ХНС основывается на многократном структурированном клиническом осмотре с применением специализированных шкал при условии исключения обратимых причин нарушения сознания. Лечение пациентов с ХНС включает в себя поддержание жизненно важных функций, обеспечение оптимального питания и борьбу с типичными осложнениями и сопутствующими состояниями (пролежни, спастичность, боль, пароксизмальная симпатическая гиперактивность и др.). У пациентов с ХНС должна проводиться реабилитация с участием мультидисциплинарной реабилитационной команды в объеме, который определяется проблемами и возможностями конкретного пациента. Наиболее эффективной реабилитация является при условии ее раннего начала. На данный момент однозначных доказательств эффективности каких-либо специфических методов, направленных на восстановление сознания, не получено; изучается ряд соответствующих фармакологических и нефармакологических вмешательств, обязательным условием применения которых является максимально возможная коррекция соматических проблем пациента. Важную роль в ведении пациентов с ХНС играет вовлечение близких пациента, которые, в свою очередь, нуждаются в получении объективной практической информации о состоянии своего родственника и о направлениях реабилитации, а также в психологической помощи.