Graph neural network based unsupervised influential sample selection for brain multigraph population fusion

Kurucu, Mert Can; Beyaz, Abdurrahman

doi:10.1016/j.compmedimag.2023.102274

Cited by 6 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A graph-based approach entails two self-evident ramifications for brain networks: the multi-scale approach-in both time [97] and space [98] and the involvement of Graph Neural Networks [99][100][101][102][103] or similarly-flavoured neural network techniques [104,105]notwithstanding the aforementioned caveats.…”

Section: Discussionmentioning

confidence: 99%

An Agent-Based Model to Reproduce the Boolean Logic Behaviour of Neuronal Self-Organised Communities through Pulse Delay Modulation and Generation of Logic Gates

Irastorza-Valera,

Benítez,

Montáns

et al. 2024

Biomimetics

View full text Add to dashboard Cite

The human brain is arguably the most complex “machine” to ever exist. Its detailed functioning is yet to be fully understood, let alone modelled. Neurological processes have logical signal-processing and biophysical aspects, and both affect the brain’s structure, functioning and adaptation. Mathematical approaches based on both information and graph theory have been extensively used in an attempt to approximate its biological functioning, along with Artificial Intelligence frameworks inspired by its logical functioning. In this article, an approach to model some aspects of the brain learning and signal processing is presented, mimicking the metastability and backpropagation found in the real brain while also accounting for neuroplasticity. Several simulations are carried out with this model to demonstrate how dynamic neuroplasticity, neural inhibition and neuron migration can reshape the brain’s logical connectivity to synchronise signal processing and obtain certain target latencies. This work showcases the importance of dynamic logical and biophysical remodelling in brain plasticity. Combining mathematical (agents, graph theory, topology and backpropagation) and biomedical ingredients (metastability, neuroplasticity and migration), these preliminary results prove complex brain phenomena can be reproduced—under pertinent simplifications—via affordable computations, which can be construed as a starting point for more ambitiously accurate simulations.

show abstract

Section: Discussionmentioning

confidence: 99%

An Agent-Based Model to Reproduce the Boolean Logic Behaviour of Neuronal Self-Organised Communities through Pulse Delay Modulation and Generation of Logic Gates

Irastorza-Valera,

Benítez,

Montáns

et al. 2024

Biomimetics

View full text Add to dashboard Cite

show abstract

“…Such parameters have already been studied on a brain regional level [87, 88, 89, 90], but not on a neuron level like suggested here. A graph-based approach entails two self-evident ramifications for brain networks: the multi-scale approach - in both time [91] and space [92] and the involvement of Graph Neural Networks [93, 94, 95, 96, 97] or similarly-flavoured neural network techniques [98, 99] - notwithstanding the aforementioned caveats.…”

Section: Discussionmentioning

confidence: 99%

An agent based model (ABM) to reproduce the boolean logic behaviour of neuronal self organized communities through pulse delay modulation and generation of logic gates

Irastorza-Valera,

Benitez,

Montáns

et al. 2023

Preprint

View full text Add to dashboard Cite

The human brain is arguably the most complex “machine” to ever exist. Its detailed functioning is yet to be fully understood, let alone modeled. Neurological processes have logical signal-processing aspects and biophysical aspects, and both affect the brain structure, functioning and adaptation. Mathematical approaches based on both information and graph theory have been extensively used in an attempt to approximate its biological functioning, along with Artificial Intelligence approaches inspired by its logical functioning. In this article, we present an approach to model some aspects of the brain learning and signal processing, mimicking the metastability and backpropagation found in the real brain while also accounting for neuroplasticity. Several simulations are carried out with this model, to demonstrate how dynamic neuroplasticity, neural inhibition and neurons migration can remodel the brain logical connectivity to syncronize signal processing and obtain target latencies. This work demonstrates the importance of dynamic logical and biophysical remodelling in brain plasticity.

show abstract

“…Graph (neural) networks are also pertinent because of their ability to capture the network’s topology—that is, structural connectivity [ 460 ]—and include it into the information flow, with the backbone of graph theory behind it [ 238 , 312 , 461 , 462 , 463 ]. Some examples have already been cited, providing promising results [ 28 , 31 , 32 ]. GNNs can be further empowered by considering the fractal nature of dendrites, again a result of evolutionary structural and functional adaptability [ 464 ].…”

Section: Modelling Approachesmentioning

confidence: 99%

“…Although data are relatively abundant, data might not be representative enough [ 19 , 20 , 21 ]. In order to obtain a better panorama of the current situation, new data managing approaches have become widespread, such as data mining [ 22 , 23 , 24 ] and machine learning [ 25 , 26 ]—especially graph neural networks [ 27 , 28 , 29 , 30 , 31 , 32 , 33 ].…”

Section: Introductionmentioning

confidence: 99%

Review of the Brain’s Behaviour after Injury and Disease for Its Application in an Agent-Based Model (ABM)

Irastorza-Valera,

Soria-Gómez,

Benitez

et al. 2024

Biomimetics

View full text Add to dashboard Cite

The brain is the most complex organ in the human body and, as such, its study entails great challenges (methodological, theoretical, etc.). Nonetheless, there is a remarkable amount of studies about the consequences of pathological conditions on its development and functioning. This bibliographic review aims to cover mostly findings related to changes in the physical distribution of neurons and their connections—the connectome—both structural and functional, as well as their modelling approaches. It does not intend to offer an extensive description of all conditions affecting the brain; rather, it presents the most common ones. Thus, here, we highlight the need for accurate brain modelling that can subsequently be used to understand brain function and be applied to diagnose, track, and simulate treatments for the most prevalent pathologies affecting the brain.

show abstract

Graph neural network based unsupervised influential sample selection for brain multigraph population fusion

Cited by 6 publications

References 42 publications

An Agent-Based Model to Reproduce the Boolean Logic Behaviour of Neuronal Self-Organised Communities through Pulse Delay Modulation and Generation of Logic Gates

An Agent-Based Model to Reproduce the Boolean Logic Behaviour of Neuronal Self-Organised Communities through Pulse Delay Modulation and Generation of Logic Gates

An agent based model (ABM) to reproduce the boolean logic behaviour of neuronal self organized communities through pulse delay modulation and generation of logic gates

Review of the Brain’s Behaviour after Injury and Disease for Its Application in an Agent-Based Model (ABM)

Contact Info

Product

Resources

About