Automated detection of soma location and morphology in neuronal network cultures

Burcin Ozcan, Pooran Negi, Fernanda Laezza, Manos Papadakis, Demetrio Labate

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Automated identification of the primary components of a neuron and extraction of its subcellular features are essential steps in many quantitative studies of neuronal networks. The focus of this paper is the development of an algorithm for the automated detection of the location and morphology of somas in confocal images of neuronal network cultures. This problem is motivated by applications in high-content screenings (HCS), where the extraction of multiple morphological features of neurons on large data sets is required. Existing algorithms are not very efficient when applied to the analysis of confocal image stacks of neuronal cultures. In addition to the usual difficulties associated with the processing of fluorescent images, these types of stacks contain a small number of images so that only a small number of pixels are available along the z-direction and it is challenging to apply conventional 3D filters. The algorithm we present in this paper applies a number of innovative ideas from the theory of directional multiscale representations and involves the following steps: (i) image segmentation based on support vector machines with specially designed multiscale filters; (ii) soma extraction and separation of contiguous somas, using a combination of level set method and directional multiscale filters. We also present an approach to extract the soma's surface morphology using the 3D shearlet transform. Extensive numerical experiments show that our algorithms are computationally efficient and highly accurate in segmenting the somas and separating contiguous ones. The algorithms presented in this paper will facilitate the development of a high-throughput quantitative platform for the study of neuronal networks for HCS applications.

Original languageEnglish (US)
Article numbere0121886
JournalPLoS One
Volume10
Issue number4
DOIs
StatePublished - Apr 8 2015

Fingerprint

Carisoprodol
Neurons
Screening
neurons
screening
Image segmentation
Surface morphology
Support vector machines
Pixels
Throughput
extracts
Processing
Experiments

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Automated detection of soma location and morphology in neuronal network cultures. / Ozcan, Burcin; Negi, Pooran; Laezza, Fernanda; Papadakis, Manos; Labate, Demetrio.

In: PLoS One, Vol. 10, No. 4, e0121886, 08.04.2015.

Research output: Contribution to journalArticle

Ozcan, Burcin ; Negi, Pooran ; Laezza, Fernanda ; Papadakis, Manos ; Labate, Demetrio. / Automated detection of soma location and morphology in neuronal network cultures. In: PLoS One. 2015 ; Vol. 10, No. 4.
@article{5a98f030fae348808fdcdf97ce1dba43,
title = "Automated detection of soma location and morphology in neuronal network cultures",
abstract = "Automated identification of the primary components of a neuron and extraction of its subcellular features are essential steps in many quantitative studies of neuronal networks. The focus of this paper is the development of an algorithm for the automated detection of the location and morphology of somas in confocal images of neuronal network cultures. This problem is motivated by applications in high-content screenings (HCS), where the extraction of multiple morphological features of neurons on large data sets is required. Existing algorithms are not very efficient when applied to the analysis of confocal image stacks of neuronal cultures. In addition to the usual difficulties associated with the processing of fluorescent images, these types of stacks contain a small number of images so that only a small number of pixels are available along the z-direction and it is challenging to apply conventional 3D filters. The algorithm we present in this paper applies a number of innovative ideas from the theory of directional multiscale representations and involves the following steps: (i) image segmentation based on support vector machines with specially designed multiscale filters; (ii) soma extraction and separation of contiguous somas, using a combination of level set method and directional multiscale filters. We also present an approach to extract the soma's surface morphology using the 3D shearlet transform. Extensive numerical experiments show that our algorithms are computationally efficient and highly accurate in segmenting the somas and separating contiguous ones. The algorithms presented in this paper will facilitate the development of a high-throughput quantitative platform for the study of neuronal networks for HCS applications.",
author = "Burcin Ozcan and Pooran Negi and Fernanda Laezza and Manos Papadakis and Demetrio Labate",
year = "2015",
month = "4",
day = "8",
doi = "10.1371/journal.pone.0121886",
language = "English (US)",
volume = "10",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Automated detection of soma location and morphology in neuronal network cultures

AU - Ozcan, Burcin

AU - Negi, Pooran

AU - Laezza, Fernanda

AU - Papadakis, Manos

AU - Labate, Demetrio

PY - 2015/4/8

Y1 - 2015/4/8

N2 - Automated identification of the primary components of a neuron and extraction of its subcellular features are essential steps in many quantitative studies of neuronal networks. The focus of this paper is the development of an algorithm for the automated detection of the location and morphology of somas in confocal images of neuronal network cultures. This problem is motivated by applications in high-content screenings (HCS), where the extraction of multiple morphological features of neurons on large data sets is required. Existing algorithms are not very efficient when applied to the analysis of confocal image stacks of neuronal cultures. In addition to the usual difficulties associated with the processing of fluorescent images, these types of stacks contain a small number of images so that only a small number of pixels are available along the z-direction and it is challenging to apply conventional 3D filters. The algorithm we present in this paper applies a number of innovative ideas from the theory of directional multiscale representations and involves the following steps: (i) image segmentation based on support vector machines with specially designed multiscale filters; (ii) soma extraction and separation of contiguous somas, using a combination of level set method and directional multiscale filters. We also present an approach to extract the soma's surface morphology using the 3D shearlet transform. Extensive numerical experiments show that our algorithms are computationally efficient and highly accurate in segmenting the somas and separating contiguous ones. The algorithms presented in this paper will facilitate the development of a high-throughput quantitative platform for the study of neuronal networks for HCS applications.

AB - Automated identification of the primary components of a neuron and extraction of its subcellular features are essential steps in many quantitative studies of neuronal networks. The focus of this paper is the development of an algorithm for the automated detection of the location and morphology of somas in confocal images of neuronal network cultures. This problem is motivated by applications in high-content screenings (HCS), where the extraction of multiple morphological features of neurons on large data sets is required. Existing algorithms are not very efficient when applied to the analysis of confocal image stacks of neuronal cultures. In addition to the usual difficulties associated with the processing of fluorescent images, these types of stacks contain a small number of images so that only a small number of pixels are available along the z-direction and it is challenging to apply conventional 3D filters. The algorithm we present in this paper applies a number of innovative ideas from the theory of directional multiscale representations and involves the following steps: (i) image segmentation based on support vector machines with specially designed multiscale filters; (ii) soma extraction and separation of contiguous somas, using a combination of level set method and directional multiscale filters. We also present an approach to extract the soma's surface morphology using the 3D shearlet transform. Extensive numerical experiments show that our algorithms are computationally efficient and highly accurate in segmenting the somas and separating contiguous ones. The algorithms presented in this paper will facilitate the development of a high-throughput quantitative platform for the study of neuronal networks for HCS applications.

UR - http://www.scopus.com/inward/record.url?scp=84929493777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929493777&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0121886

DO - 10.1371/journal.pone.0121886

M3 - Article

VL - 10

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0121886

ER -