Personalised predictive modelling with brain-inspired spiking neural networks of longitudinal MRI neuroimaging data and the case study of dementia.

Show simple item record

dc.contributor.author Doborjeh, Maryam
dc.contributor.author Doborjeh, Zohreh
dc.contributor.author Merkin, Alexander
dc.contributor.author Bahrami, Helena
dc.contributor.author Sumich, Alexander
dc.contributor.author Krishnamurthi, Rita
dc.contributor.author Medvedev, Oleg N
dc.contributor.author Crook-Rumsey, Mark
dc.contributor.author Morgan, Catherine
dc.contributor.author Kirk, Ian
dc.contributor.author Sachdev, Perminder S
dc.contributor.author Brodaty, Henry
dc.contributor.author Kang, Kristan
dc.contributor.author Wen, Wei
dc.contributor.author Feigin, Valery
dc.contributor.author Kasabov, Nikola
dc.coverage.spatial United States
dc.date.accessioned 2022-01-19T00:49:48Z
dc.date.available 2022-01-19T00:49:48Z
dc.date.issued 2021-9-20
dc.identifier.issn 0893-6080
dc.identifier.uri https://hdl.handle.net/2292/58030
dc.description.abstract <h4>Background</h4>Longitudinal neuroimaging provides spatiotemporal brain data (STBD) measurement that can be utilised to understand dynamic changes in brain structure and/or function underpinning cognitive activities. Making sense of such highly interactive information is challenging, given that the features manifest intricate temporal, causal relations between the spatially distributed neural sources in the brain.<h4>Methods</h4>The current paper argues for the advancement of deep learning algorithms in brain-inspired spiking neural networks (SNN), capable of modelling structural data across time (longitudinal measurement) and space (anatomical components). The paper proposes a methodology and a computational architecture based on SNN for building personalised predictive models from longitudinal brain data to accurately detect, understand, and predict the dynamics of an individual's functional brain state. The methodology includes finding clusters of similar data to each individual, data interpolation, deep learning in a 3-dimensional brain-template structured SNN model, classification and prediction of individual outcome, visualisation of structural brain changes related to the predicted outcomes, interpretation of results, and individual and group predictive marker discovery.<h4>Results</h4>To demonstrate the functionality of the proposed methodology, the paper presents experimental results on a longitudinal magnetic resonance imaging (MRI) dataset derived from 175 older adults of the internationally recognised community-based cohort Sydney Memory and Ageing Study (MAS) spanning 6 years of follow-up.<h4>Significance</h4>The models were able to accurately classify and predict 2 years ahead of cognitive decline, such as mild cognitive impairment (MCI) and dementia with 95% and 91% accuracy, respectively. The proposed methodology also offers a 3-dimensional visualisation of the MRI models reflecting the dynamic patterns of regional changes in white matter hyperintensity (WMH) and brain volume over 6 years.<h4>Conclusion</h4>The method is efficient for personalised predictive modelling on a wide range of neuroimaging longitudinal data, including also demographic, genetic, and clinical data. As a case study, it resulted in finding predictive markers for MCI and dementia as dynamic brain patterns using MRI data.
dc.format.medium Print-Electronic
dc.language eng
dc.publisher Elsevier BV
dc.relation.ispartofseries Neural networks : the official journal of the International Neural Network Society
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm
dc.subject Classification
dc.subject Dementia
dc.subject Longitudinal MRI data
dc.subject Personalised modelling
dc.subject Prediction
dc.subject Spiking neural networks
dc.subject Aged
dc.subject Brain
dc.subject Cognitive Dysfunction
dc.subject Dementia
dc.subject Humans
dc.subject Magnetic Resonance Imaging
dc.subject Neural Networks, Computer
dc.subject Neuroimaging
dc.subject Science & Technology
dc.subject Technology
dc.subject Life Sciences & Biomedicine
dc.subject Computer Science, Artificial Intelligence
dc.subject Neurosciences
dc.subject Computer Science
dc.subject Neurosciences & Neurology
dc.subject Personalised modelling
dc.subject Spiking neural networks
dc.subject Longitudinal MRI data
dc.subject Dementia
dc.subject Classification
dc.subject Prediction
dc.subject MILD COGNITIVE IMPAIRMENT
dc.subject WHITE-MATTER HYPERINTENSITIES
dc.subject TIMING-DEPENDENT PLASTICITY
dc.subject ALZHEIMERS-DISEASE
dc.subject SEGMENTATION
dc.subject PATTERN
dc.subject PROGRESSION
dc.subject HIPPOCAMPUS
dc.subject PREVALENCE
dc.subject POPULATION
dc.title Personalised predictive modelling with brain-inspired spiking neural networks of longitudinal MRI neuroimaging data and the case study of dementia.
dc.type Journal Article
dc.identifier.doi 10.1016/j.neunet.2021.09.013
pubs.begin-page 522
pubs.volume 144
dc.date.updated 2021-12-14T01:42:00Z
dc.rights.holder Copyright: The author en
pubs.author-url https://www.ncbi.nlm.nih.gov/pubmed/34619582
pubs.end-page 539
pubs.publication-status Published
dc.rights.accessrights http://purl.org/eprint/accessRights/RetrictedAccess en
pubs.subtype Journal Article
pubs.elements-id 867387
dc.identifier.eissn 1879-2782
dc.identifier.pii S0893-6080(21)00363-4


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics