4.7 Article

Amortized Bayesian inference on generative dynamical network models of epilepsy using deep neural density estimators

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 Cell Biology

Delineating epileptogenic networks using brain imaging data and personalized modeling in drug-resistant epilepsy

Huifang E. Wang et al.

Summary: We propose a virtual epileptic patient (VEP) workflow that uses personalized brain models and machine learning methods to estimate epileptogenic zone networks (EZNs) and aid surgical strategies. By sampling and optimizing personalized model parameters using functional stereoelectroencephalography recordings, the VEP accurately determines a patient's EZN. Additionally, the VEP can predict surgical outcomes using virtual surgeries.

SCIENCE TRANSLATIONAL MEDICINE (2023)

Article Computer Science, Artificial Intelligence

ALVLS: Adaptive local variances-Based levelset framework for medical images segmentation

Xiu Shu et al.

Summary: Medical image segmentation is a challenging task due to the non-uniform intensity and noise impact. The proposed ALVLS model, based on adaptive local variances, effectively segments medical images with intensity inhomogeneity and noises. Experimental results demonstrate its accuracy, efficiency, and robustness to noise.

PATTERN RECOGNITION (2023)

Article Multidisciplinary Sciences

Characterization of regional differences in resting-state fMRI with a data-driven network model of brain dynamics

Viktor Sip et al.

Summary: Model-based data analysis is used to link observed data to model parameters in a network of neural masses, with recent studies focusing on the role of regional variance of model parameters. This study introduces a method to infer the neural mass model representing regional dynamics and region- and subject-specific parameters from functional data, while considering the known network structure. Applied to human resting-state fMRI, the study reveals that the underlying dynamics can be described as noisy fluctuations around a fixed point, and identifies three regional parameters with distinct roles in the dynamics, one of which is strongly correlated with gene expression spatial patterns. This approach provides a novel way to analyze resting-state fMRI and has potential applications in understanding brain dynamics during aging or neurodegeneration.

SCIENCE ADVANCES (2023)

Article Neurosciences

Brain simulation as a cloud service: The Virtual Brain on EBRAINS

Michael Schirner et al.

Summary: The Virtual Brain (TVB) is an open-source service on the cloud research platform EBRAINS, providing software for constructing, simulating and analyzing brain network models. It offers features such as MRI processing pipelines and automatic conversion of model equations, facilitating online collaboration and data discovery.

NEUROIMAGE (2022)

Article Multidisciplinary Sciences

Adaptive Monte Carlo augmented with normalizing flows

Marylou Gabrie et al.

Summary: This article introduces an adaptive MCMC algorithm that enhances sampling from high-dimensional, multimodal probability distributions by using generative models as parameterized nonlocal transition kernels. The algorithm effectively samples across large free energy barriers and shows significant acceleration compared to traditional MCMC algorithms.

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

Article Neurosciences

Linking Brain Structure, Activity, and Cognitive Function through Computation

Katrin Amunts et al.

Summary: Understanding the human brain is a Grand Challenge for 21st century research. Computational approaches and dynamic generative multiscale models are instrumental for linking brain structure and function. The intersection of neuroscience, computing, and robotics has the potential to advance neuro-inspired technologies. To facilitate research sharing and collaboration, the Human Brain Project has launched the digital neuroscience research infrastructure EBRAINS.

ENEURO (2022)

Article Computer Science, Information Systems

Learning Adaptive Spatial-Temporal Context-Aware Correlation Filters for UAV Tracking

Di Yuan et al.

Summary: This paper proposes an adaptive spatial-temporal context-aware (ASTCA) model within the DCF-based tracking framework to improve tracking accuracy and reduce background interference in UAV-tracking scenarios. The ASTCA model learns spatial-temporal context weight and incorporates spatial context information, which outperforms state-of-the-art tracking methods on standard UAV datasets.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2022)

Article Biology

Flexible and efficient simulation-based inference for models of decision-making

Jan Boelts et al.

Summary: Inferring parameters of computational models is crucial in cognitive neuroscience. Simulation-based inference (SBI) using neural density estimators provides a more efficient way to capture decision-making data. Compared to traditional methods, this approach demonstrates higher accuracy and training efficiency.
Review Computer Science, Artificial Intelligence

Normalizing Flows: An Introduction and Review of Current Methods

Ivan Kobyzev et al.

Summary: Normalizing Flows are generative models that can produce tractable distributions, enabling efficient and accurate sampling and density evaluation. This survey article aims to provide a coherent and comprehensive review of the literature on the construction and use of Normalizing Flows for distribution learning, offering context and explanation of the models, reviewing current state-of-the-art literature, and identifying open questions and promising future directions.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Biochemical Research Methods

Data-driven method to infer the seizure propagation patterns in an epileptic brain from intracranial electroencephalography

Viktor Sip et al.

Summary: The study introduces a method to infer the unobserved parts of epileptic seizure based on incomplete observations, utilizing patient-specific connectome for analysis. Surgical interventions in epileptic patients have a success rate of 60-70%, partly due to incomplete spatial sampling by implanted intracranial electrodes.

PLOS COMPUTATIONAL BIOLOGY (2021)

Article Biology

Identifying spatio-temporal seizure propagation patterns in epilepsy using Bayesian inference

Anirudh N. Vattikonda et al.

Summary: Vattikonda et al. developed a conceptual mathematical model and used personalized brain connectivity information to successfully predict surgical outcomes for some patients. Their proposed hierarchical probabilistic model based on a phenomenological model of seizure dynamics shows potential as a valuable tool for clinicians to identify the seizure focus.

COMMUNICATIONS BIOLOGY (2021)

Article Multidisciplinary Sciences

Noninvasive high-frequency oscillations riding spikes delineates epileptogenic sources

Zhengxiang Cai et al.

Summary: High-frequency oscillations (HFOs) serve as a promising biomarker for localizing epileptogenic brain and guiding successful neurosurgery. The consistent concurrence of HFOs with epileptiform spikes (pHFOs) offers a tractable means to automatically identify pathological HFOs, enhancing presurgical diagnosis and postsurgical evaluation. This method shows significant improvements in localization of epileptogenic tissue and surgical outcomes, particularly in patients with multitype spikes.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Article Multidisciplinary Sciences

Density estimation using deep generative neural networks

Qiao Liu et al.

Summary: Density estimation is a fundamental problem in statistics and machine learning, and Roundtrip is a computational framework for general-purpose density estimation based on deep generative neural networks. Roundtrip retains the generative power of deep generative models while also providing estimates of density values, supporting both data generation and density estimation. It enables the use of more general mappings where the target density is modeled by learning a manifold induced from a base density, exceeding state-of-the-art performance in a diverse range of density estimation tasks.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Article Biology

Likelihood approximation networks (LANs) for fast inference of simulation models in cognitive neuroscience

Alexander Fengler et al.

Summary: In cognitive neuroscience, computational modeling is important but limited by the number of models with known likelihood functions. Using neural networks to learn approximate likelihoods allows fast recovery of parameter distributions for future inference.
Article Neurosciences

Adiabatic dynamic causal modelling

Amirhossein Jafarian et al.

Summary: Adiabatic dynamic causal modelling is a method for inferring slow changes in biophysical parameters controlling fast neuronal fluctuations. It relies on established neural mass models and an adiabatic approximation to summarize fast neuronal states using second order statistics. The method introduces a circular causality involving synaptic parameters and neuronal activity, and is validated through simulations and an illustrative application to seizure activity in an animal model.

NEUROIMAGE (2021)

Article Biochemical Research Methods

On the influence of prior information evaluated by fully Bayesian criteria in a personalized whole-brain model of epilepsy spread

Meysam Hashemi et al.

Summary: The study utilizes whole-brain modeling, information criteria, and cross-validation techniques to infer and validate spatial maps of epileptogenicity in different brain regions, providing accurate and reliable estimates of epileptogenicity levels.

PLOS COMPUTATIONAL BIOLOGY (2021)

Review Engineering, Biomedical

Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review

Khansa Rasheed et al.

Summary: Artificial intelligence and machine learning techniques are being utilized to advance clinical practice, particularly in early prediction of epileptic seizures. However, challenges such as inadequate data remain, requiring further research to address.

IEEE REVIEWS IN BIOMEDICAL ENGINEERING (2021)

Review Public, Environmental & Occupational Health

The Epidemiology of Epilepsy

Ettore Beghi

NEUROEPIDEMIOLOGY (2020)

Article Neurosciences

Dynamic effective connectivity

Tahereh S. Zarghami et al.

NEUROIMAGE (2020)

Article Multidisciplinary Sciences

The frontier of simulation-based inference

Kyle Cranmer et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Article Neurosciences

Comparing dynamic causal models of neurovascular coupling with fMRI and EEG/MEG

Amirhossein Jafarian et al.

NEUROIMAGE (2020)

Article Biology

A taxonomy of seizure dynamotypes

Maria Luisa Saggio et al.

Article Biochemical Research Methods

Controlling seizure propagation in large-scale brain networks

Simona Olmi et al.

PLOS COMPUTATIONAL BIOLOGY (2019)

Article Clinical Neurology

High-Frequency Oscillations Are Not Better Biomarkers of Epileptogenic Tissues Than Spikes

Nicolas Roehri et al.

ANNALS OF NEUROLOGY (2018)

Article Computer Science, Artificial Intelligence

Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram

Nhan Duy Truong et al.

NEURAL NETWORKS (2018)

Article Neurosciences

A generative model of whole-brain effective connectivity

Stefan Frassle et al.

NEUROIMAGE (2018)

Article Multidisciplinary Sciences

Predicting the spatiotemporal diversity of seizure propagation and termination in human focal epilepsy

Timothee Proix et al.

NATURE COMMUNICATIONS (2018)

Article Computer Science, Information Systems

Deep Learning Applications in Medical Image Analysis

Justin Ker et al.

IEEE ACCESS (2018)

Review Clinical Neurology

Seizure prediction - ready for a new era

Levin Kuhlmann et al.

NATURE REVIEWS NEUROLOGY (2018)

Review Statistics & Probability

Accelerating MCMC algorithms

Christian P. Robert et al.

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS (2018)

Review Clinical Neurology

Defining epileptogenic networks: Contribution of SEEG and signal analysis

Fabrice Bartolomei et al.

EPILEPSIA (2017)

Article Computer Science, Interdisciplinary Applications

Stan: A Probabilistic Programming Language

Bob Carpenter et al.

JOURNAL OF STATISTICAL SOFTWARE (2017)

Article Computer Science, Artificial Intelligence

A survey on deep learning in medical image analysis

Geert Litjens et al.

MEDICAL IMAGE ANALYSIS (2017)

Article Neurosciences

Regression DCM for fMRI

Stefan Frassle et al.

NEUROIMAGE (2017)

Article Clinical Neurology

Individual brain structure and modelling predict seizure propagation

Timothee Proix et al.

Review Clinical Neurology

Implantation of Stereoelectroencephalography Electrodes: A Systematic Review

Francesco Cardinale et al.

JOURNAL OF CLINICAL NEUROPHYSIOLOGY (2016)

Article Mathematical & Computational Biology

How the cortico-thalamic feedback affects the EEG power spectrum over frontal and occipital regions during propofol-induced sedation

Meysam Hashemi et al.

JOURNAL OF COMPUTATIONAL NEUROSCIENCE (2015)

Article Neurosciences

Distinct EEG seizure patterns reflect different seizure generation mechanisms

Pariya Salami et al.

JOURNAL OF NEUROPHYSIOLOGY (2015)

Article Medicine, Research & Experimental

Seizures and Epilepsy: An Overview for Neuroscientists

Carl E. Stafstrom et al.

COLD SPRING HARBOR PERSPECTIVES IN MEDICINE (2015)

Article Clinical Neurology

On the nature of seizure dynamics

Viktor K. Jirsa et al.

Article Neurosciences

Permittivity Coupling across Brain Regions Determines Seizure Recruitment in Partial Epilepsy

Timothee Proix et al.

JOURNAL OF NEUROSCIENCE (2014)

Article Neurosciences

Anesthetic action on extra-synaptic receptors: effects in neural population models of EEG activity

Meysam Hashemi et al.

FRONTIERS IN SYSTEMS NEUROSCIENCE (2014)

Article Clinical Neurology

High-frequency oscillations as a new biomarker in epilepsy

Maeike Zijlmans et al.

ANNALS OF NEUROLOGY (2012)

Review Neurosciences

FreeSurfer

Bruce Fischl

NEUROIMAGE (2012)

Article Cell Biology

Addressing parameter identifiability by model-based experimentation

A. Raue et al.

IET SYSTEMS BIOLOGY (2011)

Review Neurosciences

Emerging concepts for the dynamical organization of resting-state activity in the brain

Gustavo Deco et al.

NATURE REVIEWS NEUROSCIENCE (2011)

Review Ecology

Approximate Bayesian Computation in Evolution and Ecology

Mark A. Beaumont

ANNUAL REVIEW OF ECOLOGY, EVOLUTION, AND SYSTEMATICS, VOL 41 (2010)

Article Mathematics, Applied

Variational Bayesian identification and prediction of stochastic nonlinear dynamic causal models

J. Daunizeau et al.

PHYSICA D-NONLINEAR PHENOMENA (2009)

Article Multidisciplinary Sciences

Key role of coupling, delay, and noise in resting brain fluctuations

Gustavo Deco et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2009)

Article Neurosciences

Dynamic causal modelling

KJ Friston et al.

NEUROIMAGE (2003)