prikaz prve stranice dokumenta Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture
  Download
PDF 2.66 MB
Scientific paper - Original scientific paper
Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture
Scientific Reports, 13 (2023), 1; 5567. https://doi.org/10.1038/s41598-023-32154-x
Štajduhar, Andrija; Lipić, Tomislav; Lončarić, Sven; Judaš, Miloš; Sedmak, Goran

Institutional repository: Dr Med - University of Zagreb School of Medicine Digital Repository

Cite this document

Štajduhar, A., Lipić, T., Lončarić, S., Judaš, M. & Sedmak, G. (2023). Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture. Scientific Reports, 13. (1). doi: 10.1038/s41598-023-32154-x

Štajduhar, Andrija, et al. "Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture." Scientific Reports, vol. 13, no. 1, 2023. https://doi.org/10.1038/s41598-023-32154-x

Štajduhar, Andrija, Tomislav Lipić, Sven Lončarić, Miloš Judaš and Goran Sedmak. "Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture." Scientific Reports 13, no. 1 (2023). https://doi.org/10.1038/s41598-023-32154-x

Štajduhar, A., et al. (2023) 'Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture', Scientific Reports, 13(1). doi: 10.1038/s41598-023-32154-x

Štajduhar A, Lipić T, Lončarić S, Judaš M, Sedmak G. Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture. Scientific Reports [Internet]. 2023 April 05 [cited 2024 April 29];13(1). doi: 10.1038/s41598-023-32154-x

A. Štajduhar, T. Lipić, S. Lončarić, M. Judaš and G. Sedmak, "Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture", Scientific Reports, vol. 13, no. 1, April 2023. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:105:004091. [Accessed: 29 April 2024]

Metadata
Title (english)Interpretable machine learning approach for neuron-centric analysis of human cortical cytoarchitecture
AuthorAndrija Štajduhar
AuthorTomislav Lipić
AuthorSven Lončarić
AuthorMiloš Judaš
AuthorGoran Sedmak
Author's institutionUniversity of Zagreb
School of Medicine
(Croatian Institiute for Brain Research)
Author's institutionUniversity of Zagreb
School of Medicine
(Department of Anatomy and Clinical Anatomy)
Author's institutionUniversity of Zagreb
School of Medicine
(Department of Medical Statistics, Epidemiology and Medical Informatics)
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Public Health and Health Care
Epidemiology
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Basic Medical Sciences
Anatomy
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Basic Medical Sciences
Neuroscience
Abstract (english)
The complexity of the cerebral cortex underlies its function and distinguishes us as humans. Here, we present a principled veridical data science methodology for quantitative histology that shifts focus from image-level investigations towards neuron-level representations of cortical regions, with the neurons in the image as a subject of study, rather than pixel-wise image content. Our methodology relies on the automatic segmentation of neurons across whole histological sections and an extensive set of engineered features, which reflect the neuronal phenotype of individual neurons and the properties of neurons’ neighborhoods. The neuron-level representations are used in an interpretable machine learning pipeline for mapping the phenotype to cortical layers. To validate our approach, we created a unique dataset of cortical layers manually annotated by three experts in neuroanatomy and histology. The presented methodology offers high interpretability of the results, providing a deeper understanding of human cortex organization, which may help formulate new scientific hypotheses, as well as to cope with systematic uncertainty in data and model predictions.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review
Publication versionPublished version
Journal titleScientific Reports
Numberingvol. 13, no. 1, 5567
e-ISSN2045-2322
DOIhttps://doi.org/10.1038/s41598-023-32154-x
URN:NBNurn:nbn:hr:105:004091
Publication2023-04-05
Document URLhttps://www.nature.com/articles/s41598-023-32154-x
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2024-01-08 08:33:40