GMRV Publications
A Deep Learning-Based Workflow for Dendritic Spine Segmentation
Isabel Vidaurre-Gallart,
Isabel Fernaud-Espinosa,
Nicusor Cosmin-Toader,
Lidia Talavera-Martínez,
Miguel Martín-Abadal,
Ruth Benavides-Piccione,
Yolanda Gonzalez-Cid,
Luis Pastor,
Javier DeFelipe,
Marcos J. García-Lorenzo
Frontiers in Neuroanatomy, Volume 16 - march 2022
Download the publication :
The 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 themost 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.
Images and movies
BibTex references
@Article\{VFCTMBGPDG22,
author = "Vidaurre-Gallart, Isabel and Fernaud-Espinosa, Isabel and Cosmin-Toader, Nicusor and Talavera-Martínez, Lidia and Martín-Abadal, Miguel and Benavides-Piccione, Ruth and Gonzalez-Cid, Yolanda and Pastor, Luis and DeFelipe, Javier and García-Lorenzo, Marcos J.",
title = "A Deep Learning-Based Workflow for Dendritic Spine Segmentation",
journal = "Frontiers in Neuroanatomy",
volume = "16",
month = "march",
year = "2022",
keywords = "automatic 3D image segmentation, artificial neural network, confocal microscopy, reconstruction algorithms, pyramidal cells",
url = "http://gmrv.es/Publications/2022/VFCTMBGPDG22"
}
Other publications in the database