Mostrar el registro sencillo del ítem
dc.contributor.author
Moguilner, Sebastian
dc.contributor.author
Whelan, Robert
dc.contributor.author
Adams, Hieab
dc.contributor.author
Valcour, Victor
dc.contributor.author
Tagliazucchi, Enzo Rodolfo
dc.contributor.author
Ibañez, Agustin Mariano
dc.date.available
2024-01-26T13:23:32Z
dc.date.issued
2023-04
dc.identifier.citation
Moguilner, Sebastian; Whelan, Robert; Adams, Hieab; Valcour, Victor; Tagliazucchi, Enzo Rodolfo; et al.; Visual deep learning of unprocessed neuroimaging characterises dementia subtypes and generalises across non-stereotypic samples; Elsevier; eBioMedicine; 90; 4-2023; 1-15
dc.identifier.issn
2352-3964
dc.identifier.uri
http://hdl.handle.net/11336/224957
dc.description.abstract
Background: Dementia's diagnostic protocols are mostly based on standardised neuroimaging data collected in the Global North from homogeneous samples. In other non-stereotypical samples (participants with diverse admixture, genetics, demographics, MRI signals, or cultural origins), classifications of disease are difficult due to demographic and region-specific sample heterogeneities, lower quality scanners, and non-harmonised pipelines. Methods: We implemented a fully automatic computer-vision classifier using deep learning neural networks. A DenseNet was applied on raw (unpreprocessed) data from 3000 participants (behavioural variant frontotemporal dementia-bvFTD, Alzheimer's disease-AD, and healthy controls; both male and female as self-reported by participants). We tested our results in demographically matched and unmatched samples to discard possible biases and performed multiple out-of-sample validations. Findings: Robust classification results across all groups were achieved from standardised 3T neuroimaging data from the Global North, which also generalised to standardised 3T neuroimaging data from Latin America. Moreover, DenseNet also generalised to non-standardised, routine 1.5T clinical images from Latin America. These generalisations were robust in samples with heterogenous MRI recordings and were not confounded by demographics (i.e., were robust in both matched and unmatched samples, and when incorporating demographic variables in a multifeatured model). Model interpretability analysis using occlusion sensitivity evidenced core pathophysiological regions for each disease (mainly the hippocampus in AD, and the insula in bvFTD) demonstrating biological specificity and plausibility. Interpretation: The generalisable approach outlined here could be used in the future to aid clinician decision-making in diverse samples. Funding: The specific funding of this article is provided in the acknowledgements section.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Elsevier
dc.rights
info:eu-repo/semantics/openAccess
dc.rights.uri
https://creativecommons.org/licenses/by/2.5/ar/
dc.subject
COMPUTER VISION
dc.subject
DEEP LEARNING
dc.subject
DEMENTIA
dc.subject
REPRODUCIBILITY
dc.subject
UNPROCESSED MRI
dc.subject.classification
Neurociencias
dc.subject.classification
Medicina Básica
dc.subject.classification
CIENCIAS MÉDICAS Y DE LA SALUD
dc.title
Visual deep learning of unprocessed neuroimaging characterises dementia subtypes and generalises across non-stereotypic samples
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2024-01-25T10:45:31Z
dc.journal.volume
90
dc.journal.pagination
1-15
dc.journal.pais
Reino Unido
dc.description.fil
Fil: Moguilner, Sebastian. Universidad de San Andrés; Argentina. Universidad Adolfo Ibañez; Chile
dc.description.fil
Fil: Whelan, Robert. University of California; Estados Unidos
dc.description.fil
Fil: Adams, Hieab. Universidad Adolfo Ibañez; Chile
dc.description.fil
Fil: Valcour, Victor. University of California; Estados Unidos
dc.description.fil
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires; Argentina. Universidad Adolfo Ibañez; Chile
dc.description.fil
Fil: Ibañez, Agustin Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de San Andrés; Argentina. University of California; Estados Unidos. Universidad Adolfo Ibañez; Chile
dc.journal.title
eBioMedicine
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.ebiom.2023.104540
Archivos asociados