A multi-spectral myelin annotation tool for machine learning based myelin quantification.
fluorescence images
image analysis
machine learning
myelin annotation tool
myelin quantification
Journal
F1000Research
ISSN: 2046-1402
Titre abrégé: F1000Res
Pays: England
ID NLM: 101594320
Informations de publication
Date de publication:
2020
2020
Historique:
accepted:
14
11
2023
medline:
23
11
2023
pubmed:
22
11
2023
entrez:
22
11
2023
Statut:
epublish
Résumé
Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify myelin by co-localization of oligodendrocyte and axonal membranes that fit certain shape and size criteria. Because myelin wriggles along x-y-z axes, machine learning is ideal for its segmentation. However, machine-learning methods, especially convolutional neural networks (CNNs), require a high number of annotated images, which necessitate expert labor. To facilitate myelin annotation, we developed a workflow and software for myelin ground truth extraction from multi-spectral fluorescent images. Additionally, to the best of our knowledge, for the first time, a set of annotated myelin ground truths for machine learning applications were shared with the community.
Identifiants
pubmed: 37990695
doi: 10.12688/f1000research.27139.4
pmc: PMC10660289
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1492Informations de copyright
Copyright: © 2023 Çapar A et al.
Déclaration de conflit d'intérêts
No competing interests were disclosed.
Références
Cold Spring Harb Perspect Biol. 2015 Jun 22;8(1):a020479
pubmed: 26101081
Glia. 2017 Oct;65(10):1565-1589
pubmed: 28618073
Comput Methods Programs Biomed. 2022 Jun;220:106802
pubmed: 35436661
Development. 2015 Jun 15;142(12):2213-25
pubmed: 26015546
J Neurosci Methods. 2020 Dec 1;346:108946
pubmed: 32931810
N Engl J Med. 2018 Jan 11;378(2):169-180
pubmed: 29320652