☆ 4.5 Article

The potential of convolutional neural networks for identifying neural states based on electrophysiological signals: experiments on synthetic and real patient data

FRONTIERS IN HUMAN NEUROSCIENCE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Clinical Neurology

A practical guide to invasive neurophysiology in patients with deep brain stimulation

Wolf-Julian Neumann et al.

CLINICAL NEUROPHYSIOLOGY (2022)

添加到收藏夹

Article Neurosciences

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation

Timon Merk et al.

Summary: Sensing enabled implantable devices and next-generation neurotechnology enable real-time adjustments of invasive neuromodulation. Machine learning holds the potential for expanding the clinical utility of demand dependent adaptive deep brain stimulation (aDBS) and may be the next breakthrough in the therapeutic success of clinical brain computer interfaces. This review summarizes the current state of machine learning studies for invasive neurophysiology, including the transformation of brain recordings into meaningful features for symptom and behavior decoding. It also explains commonly used machine learning models and reviews good practices for training and testing to ensure real-time adaptation in clinical settings. The review highlights the first studies combining machine learning with aDBS and identifies key ingredients for successful clinical adoption: multidisciplinary research teams, publicly available datasets, open-source algorithmic solutions, and strong worldwide research collaborations.

EXPERIMENTAL NEUROLOGY (2022)

添加到收藏夹

Article Biology

Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease

Timon Merk et al.

Summary: This study developed an invasive brain signal decoding approach using intraoperative sensorimotor electrocorticography (ECoG) and subthalamic LFP to predict grip-force in Parkinson's disease patients undergoing DBS. The results showed that ECoG outperformed subthalamic LFP for accurate grip-force decoding, and gradient boosted decision trees (XGBOOST) showed the best performance. ECoG based decoding performance negatively correlated with motor impairment, highlighting the impact of PD pathophysiology on movement encoding capacity.

ELIFE (2022)

添加到收藏夹

Article Psychology, Biological

Decoding naturalistic affective behaviour from spectro-spatial features in multiday human iEEG

Maryam Bijanzadeh et al.

Summary: This study shows that brain networks encode naturalistic affective behaviours through increased high-frequency and decreased low-frequency activity across the mesolimbic network. The insula and anterior cingulate cortex play critical roles in differentiating behaviours with observable affect from those without.

NATURE HUMAN BEHAVIOUR (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Deep neural networks constrained by neural mass models improve electrophysiological source imaging of spatiotemporal brain dynamics

Rui Sun et al.

Summary: This article introduces a non-conventional deep learning-based source imaging framework called DeepSIF, which provides robust and precise spatiotemporal estimates of underlying brain dynamics from noninvasive high-density electroencephalography (EEG) recordings. The performance of DeepSIF is evaluated through various experiments and it demonstrates superior performance in imaging sensory and cognitive brain responses as well as identifying epileptogenic regions.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2022)

添加到收藏夹

Article Cell Biology

Principles of gait encoding in the subthalamic nucleus of people with Parkinson's disease

Yohann Thenaisie et al.

Summary: The disruption of subthalamic nucleus dynamics in Parkinson's disease has been found to impair walking. Researchers have developed a neurorobotic platform to investigate how the subthalamic nucleus encodes the key components of walking. They discovered that the subthalamic nucleus encodes the initiation, termination, and amplitude of leg muscle activation during walking. These findings can potentially be used to improve walking in people with Parkinson's disease using neuroprosthetic systems.

SCIENCE TRANSLATIONAL MEDICINE (2022)

添加到收藏夹

Article Biology

A deep learning based model using RNN-LSTM for the Detection of Schizophrenia from EEG data

Rinku Supakar et al.

Summary: The study proposed a deep learning model based on EEG analysis to diagnose schizophrenia and achieved high accuracy with optimized feature sets. The proposed model outperformed traditional machine learning classifiers.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

添加到收藏夹

Article Neurosciences

Theta power and theta-gamma coupling support long-term spatial memory retrieval

Umesh Vivekananda et al.

Summary: In a study involving presurgical epilepsy patients undergoing intracranial EEG recording, increased theta power in two discrete bands during cued retrieval was found to be associated with improved task performance in long-term spatial memory. Additionally, increased coupling between low theta phase and gamma amplitude during the same period was also correlated with better task performance. Furthermore, it was observed that low and high gamma amplitude peaked at different phases of the theta cycle, providing a novel connection between human hippocampal function and rodent data.

HIPPOCAMPUS (2021)

添加到收藏夹

Article Engineering, Biomedical

Generalized neural decoders for transfer learning across participants and recording modalities

Steven M. Peterson et al.

Summary: The study introduces a new decoder, HTNet, utilizing a convolutional neural network with innovative techniques. HTNet outperformed state-of-the-art decoders when tested on unseen participants, demonstrating its ability to generalize to new participants and recording modalities. Additionally, fine-tuning HTNet with minimal data allows for performance comparable to tailored decoders.

JOURNAL OF NEURAL ENGINEERING (2021)

添加到收藏夹

Article Clinical Neurology

Closed-Loop Deep Brain Stimulation for Essential Tremor Based on Thalamic Local Field Potentials

Shenghong He et al.

Summary: The study proposed an innovative approach for essential tremor treatment by detecting tremor-provoking movements and delivering stimulation in real-time, achieving effective therapeutic outcomes. Results showed a high percentage of stimulation time when tremors were triggered, with tremor suppression achieved while conserving energy.

MOVEMENT DISORDERS (2021)

添加到收藏夹

Article Mathematical & Computational Biology

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Afshin Shoeibi et al.

Summary: This study proposes various intelligent deep learning methods for automated schizophrenia diagnosis using EEG signals, compared with conventional methods. Using the dataset from the Institute of Psychiatry and Neurology in Warsaw, Poland, the study divided EEG signals into time frames, normalized them, and employed different classification approaches, with the CNN-LSTM architecture showing the best performance in SZ diagnosis.

FRONTIERS IN NEUROINFORMATICS (2021)

添加到收藏夹

Article Clinical Neurology

Clinical perspectives of adaptive deep brain stimulation

Matteo Guidetti et al.

Summary: Adaptive deep brain stimulation (aDBS) shows promise in treating movement disorders, but its application in cognitive and psychiatric disorders remains challenging.

BRAIN STIMULATION (2021)

添加到收藏夹

Article Neurosciences

Within-cycle instantaneous frequency profiles report oscillatory waveform dynamics

Andrew J. Quinn et al.

Summary: This study introduces an analytical framework for quantifying nonsinusoidal waveform shapes in neuronal oscillations. Using a masked empirical mode decomposition method, the study shows that instantaneous frequency accurately tracks nonsinusoidal shapes. The research also demonstrates how principal component analysis can identify theta cycle waveform motifs associated with cycle amplitude, duration, and animal movement speed.

JOURNAL OF NEUROPHYSIOLOGY (2021)

添加到收藏夹

Review Clinical Neurology

Habituation After Deep Brain Stimulation in Tremor Syndromes: Prevalence, Risk Factors and Long-Term Outcomes

James Peters et al.

Summary: Deep brain stimulation is an effective treatment for essential, dystonic, and Parkinson's tremor, but long-term benefit can be reduced due to stimulation tolerance or habituation. The exact mechanisms and management of habituation in DBS for tremor syndromes remain unclear and challenging.

FRONTIERS IN NEUROLOGY (2021)

添加到收藏夹

Article Engineering, Biomedical

Learning Invariant Patterns Based on a Convolutional Neural Network and Big Electroencephalography Data for Subject-Independent P300 Brain-Computer Interfaces

Wei Gao et al.

Summary: This study proposed an invariant pattern learning method based on CNN and big EEG data for subject-independent P300 BCIs. By analyzing EEG data from 200 subjects, it was found that almost all subjects obtained significant cross-subject and cross-amplifier effects, with an average accuracy of more than 80%.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Ramprasaath R. Selvaraju et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2020)

添加到收藏夹

Editorial Material Clinical Neurology

Debugging Adaptive Deep Brain Stimulation for Parkinson's Disease

Simon Little et al.

MOVEMENT DISORDERS (2020)

添加到收藏夹

Article Biochemical Research Methods

LFP-Net: A deep learning framework to recognize human behavioral activities using brain STN-LFP signals

Hosein M. Golshan et al.

JOURNAL OF NEUROSCIENCE METHODS (2020)

添加到收藏夹

Article Engineering, Biomedical

Rapid motor fluctuations reveal short-timescale neurophysiological biomarkers of Parkinson's disease

Minkyu Ahn et al.

JOURNAL OF NEURAL ENGINEERING (2020)

添加到收藏夹

Article Clinical Neurology

Waveform changes with the evolution of beta bursts in the human subthalamic nucleus

Chien-Hung Yeh et al.

CLINICAL NEUROPHYSIOLOGY (2020)

添加到收藏夹

Article Multidisciplinary Sciences

Phase-amplitude coupling between theta and gamma oscillations adapts to speech rate

Mikel Lizarazu et al.

ANNALS OF THE NEW YORK ACADEMY OF SCIENCES (2019)

添加到收藏夹

Article Neurosciences

Synchronised spiking activity underlies phase amplitude coupling in the subthalamic nucleus of Parkinson's disease patients

Anders Christian Meidahl et al.

NEUROBIOLOGY OF DISEASE (2019)

添加到收藏夹

Article Engineering, Biomedical

Towards Real-Time, Continuous Decoding of Gripping Force From Deep Brain Local Field Potentials

Syed Ahmar Shah et al.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2018)

添加到收藏夹

Article Neurosciences

Beta burst coupling across the motor circuit in Parkinson's disease

Gerd Tinkhauser et al.

NEUROBIOLOGY OF DISEASE (2018)

添加到收藏夹

Article Neurosciences

Nonsinusoidal Beta Oscillations Reflect Cortical Pathophysiology in Parkinson's Disease

Scott R. Cole et al.

JOURNAL OF NEUROSCIENCE (2017)

添加到收藏夹

Article Multidisciplinary Sciences

Brain network dynamics are hierarchically organized in time

Diego Vidaurre et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2017)

添加到收藏夹

Article Clinical Neurology

Adaptive deep brain stimulation for Parkinson's disease demonstrates reduced speech side effects compared to conventional stimulation in the acute setting

Simon Little et al.

JOURNAL OF NEUROLOGY NEUROSURGERY AND PSYCHIATRY (2016)

添加到收藏夹

Article Neurosciences

Measuring Phase-Amplitude Coupling Between Neuronal Oscillations of Different Frequencies

Adriano B. L. Tort et al.

JOURNAL OF NEUROPHYSIOLOGY (2010)

添加到收藏夹

Article Multidisciplinary Sciences

High gamma power is phase-locked to theta oscillations in human neocortex

R. T. Canolty et al.

SCIENCE (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.