A5081476624- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- EEG and Brain-Computer Interfaces
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Advanced Neuroimaging Techniques and Applications
- Neonatal and fetal brain pathology
- Neural and Behavioral Psychology Studies
- Autism Spectrum Disorder Research
- AI in cancer detection
- Tryptophan and brain disorders
- Machine Learning in Materials Science
- Blind Source Separation Techniques
- Explainable Artificial Intelligence (XAI)
- Mental Health Research Topics
- Gaze Tracking and Assistive Technology
- Neurobiology of Language and Bilingualism
- Fetal and Pediatric Neurological Disorders
- Topic Modeling
- Neural Networks and Applications
- COVID-19 diagnosis using AI
- Memory and Neural Mechanisms
Skolkovo Institute of Science and Technology
2018-2024
Moscow Research and Clinical Center for Neuropsychiatry
2024
University of Sharjah
2024
Institute of Higher Nervous Activity and Neurophysiology
2016-2021
Optech (Canada)
2021
Kurchatov Institute
2016-2019
Lomonosov Moscow State University
2016-2019
Russian Academy of Sciences
2019
The Default Mode Network (DMN) is a brain system that mediates internal modes of cognitive activity, showing higher neural activation when one at rest. Nowadays, there lot interest in assessing functional interactions between its key regions, but the majority studies only association BOLD (Blood-oxygen-level dependent) patterns measured, so it impossible to identify causal influences. There are some (i.e. effective connectivity), however often with inconsistent results. aim current work find...
The purpose of this paper was to study causal relationships between left and right hippocampal regions (LHIP RHIP, respectively) within the default mode network (DMN) as represented by its key structures: medial prefrontal cortex (MPFC), posterior cingulate (PCC), inferior parietal (LIPC) (RIPC) hemispheres. Furthermore, we were interested in testing stability connectivity patterns when adding or deleting interest. functional magnetic resonance imaging (fMRI) data from a group 30 healthy...
In the field of psychoneurology, analysis neuroimaging data aimed at extracting distinctive patterns pathologies, such as epilepsy and depression, is well known to represent a challenging problem. As resolution acquisition rates modern medical scanners rise, need automatically capture complex spatiotemporal in large imaging arrays suggests using automated approaches pattern recognition volumetric images, training classification models deep learning. On other hand, with typically scarce data,...
Independent Component Analysis (ICA) is a conventional approach to exclude non-brain signals such as eye movements and muscle artifacts from electroencephalography (EEG). A rejection of independent components (ICs) usually performed in semiautomatic mode requires experts' involvement. As also revealed by our study, opinions about the nature component often disagree, highlighting need develop robust sustainable automatic system for EEG ICs classification. The current article presents toolbox...
Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yet only a few applications now clinical use one of the reasons for that is poor transferability models to data from different sources or acquisition domains. Development new algorithms transfer training adaptation domain multi-modal imaging crucial development accurate their clinics. In present work, we overview used tackle shift problem machine vision. The discussed this survey include...
Background. Ideas about relationships between "I", egocentric spatial orientation and the sense of bodily "Self " date back to work by classics philosophy psychology. Cognitive neuroscience has provided knowledge brain areas involved in self-referential processing, such as rostral prefrontal, temporal parietal cortices, often active part default mode network (DMN).
Studies of active vision in naturalistic scenes show the existence two classes eye movements manifested ambient and focal visual fixations.This finding seems to corroborate with anatomical separation "streams" processing related localization (dorsal system) or identification objects (ventral system).Direct verification this connection proved be difficult due an insufficient resolution conventional noninvasive brain-imaging methods.Another hypothesis recently attributed same observation...
Major depressive disorder (MDD) is a common mental and amongst the most prevalent psychiatric disorders. MDD remains challenging to diagnose predict its onset due heterogeneous phenotype complex etiology. Hence, early detection using diagnostic biomarkers critical for rapid intervention. In this study, mixture of AI bioinformatics were used mine transcriptomic data from publicly available datasets including 170 patients 121 healthy controls. Bioinformatics analysis gene set enrichment (GSEA)...
Deep learning convolution neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of deformable deep network layers data classification. We propose new 3D convolutions (d-convolutions), implement them in VoxResNet architecture and apply structural show that d-convolutions outperform standard ones are effective unprocessed MR images being robust particular geometrical properties data. Firstly proposed dVoxResNet exhibits high use
In the present work, we study candidate biomarkers for depression disorder and + epilepsy comorbidity. Building on advanced data analysis pipeline, identify biomarkers, compare them across tasks to previous research. The classification performance achieved by our system compares favourably one reported in literature, where longer scanning sessions stronger magnetic fields were employed.
ABIDE is the largest open-source autism spectrum disorder database with both fMRI data and full phenotype description. These were extensively studied based on functional connectivity analysis as well deep learning raw data, top models accuracy close to 75% for separate scanning sites. Yet there still a problem of transferability between different sites within ABIDE. In current paper, we first time perform domain adaptation brain pathology classification neuroimaging data. We use 3D...
It has long been known that patients with depression exhibit abnormal brain functional connectivity patterns, are often studied from a graph-theoretic perspective. However, while certain simpler graph features have examined, little done in the direction of advanced feature learning methodologies such as network embeddings. Our work aims to extend understanding importance graph-based for medical applications by evaluating recently proposed anonymous walk embeddings (AWE) difficult...
The paper will provide examples of computer vision tasks in which topological data analysis gave new effective solutions. Ideas underlying and its basic methods be briefly described illustrated with problems. No prior knowledge computational geometry is assumed, a brief introduction to subject given throughout the text.
Numerous brain imaging studies have reported white matter alterations in schizophrenia, but the lipidome analysis of corresponding tissue remains incomplete. In this study, we investigated composition six subcortical regions to major axonal tracks both control subjects and schizophrenia patients. All exhibited a consistent pattern quantitative involving myelin-forming mitochondria associated lipid classes. While alteration levels lipids, particularly sphingolipids, aligned with extent myelin...
In region of interest (ROI) brain analysis, the proper selection voxels in ROIs plays a crucial role. existing methods for functionally homogeneous regions human based on fMRI data, each voxel is attributed to some region, not taking into account possibility existence borderline demonstrating transitional dynamics that cannot be clearly any between which these are located. As result, situation when formally assigned one but located opposite borders have correlation close zero or even...
The view that the left cerebral hemisphere in humans "dominates" over "subdominant" right has been so deeply entrenched neuropsychology no amount of evidence seems able to overcome it. In this article, we examine inhibitory cause-and-effect connectivity among human brain structures related different parts triune evolutionary stratification —archicortex, paleocortex and neocortex— relation early late phases a prolonged resting-state functional magnetic resonance imaging (fMRI) experiment....
In animal experiments, radial traveling waves have been recorded on the surface of cortex. humans, recording by microelectrode matrices reveals only fragments such waves. Our basic assumption is that source EEG/MEG in alpha and beta bands are Similar generated networks recurrently coupled neurons, where excitation propagated through intracortical connections. We simulated human brain compared simulation data with experimental signals evoked spontaneous MEG. Model were assigned a number...