Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/277503
COMPARTIR / EXPORTAR:
logo share SHARE logo core CORE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Invitar a revisión por pares abierta
Título

A Deep Learning-Based Workflow for Dendritic Spine Segmentation

AutorVidaurre-Gallart, I.; Fernaud-Espinosa, Isabel CSIC ORCID; Cosmin-Toader, N.; Talavera-Martínez, L; Martín-Abadal, Miguel; Benavides-Piccione, Ruth CSIC ORCID ; González-Cid, Yolanda; Pastor, L.; DeFelipe, Javier CSIC ORCID ; García-Lorenzo, M.
Palabras claveArtificial neural networks
automatic 3D image segmentation
Confocal microscopy
pyramidal cells
reconstruction algorithms
Fecha de publicación2022
EditorFrontiers Media
CitaciónFrontiers in neuroanatomy 16 (2022)
ResumenThe morphological analysis of dendritic spines is an important challenge for the neuroscientific community. Most state-of-the-art techniques rely on user-supervised algorithms to segment the spine surface, especially those designed for light microscopy images. Therefore, processing large dendritic branches is costly and time-consuming. Although deep learning (DL) models have become one of the most commonly used tools in image segmentation, they have not yet been successfully applied to this problem. In this article, we study the feasibility of using DL models to automatize spine segmentation from confocal microscopy images. Supervised learning is the most frequently used method for training DL models. This approach requires large data sets of high-quality segmented images (ground truth). As mentioned above, the segmentation of microscopy images is time-consuming and, therefore, in most cases, neuroanatomists only reconstruct relevant branches of the stack. Additionally, some parts of the dendritic shaft and spines are not segmented due to dyeing problems. In the context of this research, we tested the most successful architectures in the DL biomedical segmentation field. To build the ground truth, we used a large and high-quality data set, according to standards in the field. Nevertheless, this data set is not sufficient to train convolutional neural networks for accurate reconstructions. Therefore, we implemented an automatic preprocessing step and several training strategies to deal with the problems mentioned above. As shown by our results, our system produces a high-quality segmentation in most cases. Finally, we integrated several postprocessing user-supervised algorithms in a graphical user interface application to correct any possible artifacts.
Versión del editorhttp://dx.doi.org/10.3389/fnana.2022.817903
URIhttp://hdl.handle.net/10261/277503
DOI10.3389/fnana.2022.817903
Identificadoresdoi: 10.3389/fnana.2022.817903
issn: 1662-5129
Aparece en las colecciones: (IC) Artículos




Ficheros en este ítem:
Fichero Descripción Tamaño Formato
fnana-16-817903.pdf4,83 MBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo

CORE Recommender

SCOPUSTM   
Citations

5
checked on 25-mar-2024

WEB OF SCIENCETM
Citations

2
checked on 28-feb-2024

Page view(s)

28
checked on 28-mar-2024

Download(s)

36
checked on 28-mar-2024

Google ScholarTM

Check

Altmetric

Altmetric


Este item está licenciado bajo una Licencia Creative Commons Creative Commons