Limits...
Automated detection of soma location and morphology in neuronal network cultures.

Ozcan B, Negi P, Laezza F, Papadakis M, Labate D - PLoS ONE (2015)

Bottom Line: 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.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.

View Article: PubMed Central - PubMed

Affiliation: Dept. of Mathematics, University of Houston, Houston, Texas, United States of America.

ABSTRACT
Automated identification of the primary components of a neuron and extraction of its sub-cellular 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.

No MeSH data available.


Related in: MedlinePlus

Application of level set method to detect soma area.The figure shows a detail from a segmented image of a neuron (MIP) where colors correspond to the values of the Directional Ratio values and range between 1 (=red) and 0 (=blue). The application of the threshold value 0.9 identifies a region strictly inside the soma, with boundary curve Γ (in the left panel). The level set method evolves the boundary curve Γ with a velocity in the normal direction (indicated by the arrows in the right panel) that depends on the magnitude of the gradient of the Directional Ratio.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4390318&req=5

pone.0121886.g002: Application of level set method to detect soma area.The figure shows a detail from a segmented image of a neuron (MIP) where colors correspond to the values of the Directional Ratio values and range between 1 (=red) and 0 (=blue). The application of the threshold value 0.9 identifies a region strictly inside the soma, with boundary curve Γ (in the left panel). The level set method evolves the boundary curve Γ with a velocity in the normal direction (indicated by the arrows in the right panel) that depends on the magnitude of the gradient of the Directional Ratio.

Mentions: Recall that the level set method is a variational approach introduced to track evolution of curves and shapes without having to parameterize these objects. The main idea is to identify a curve (or interface) Γ as the zero level set of a three-dimensional level set function ϕ and to follow the changes of Γ = {(x, y) : ϕ(x, y) = 0} from the evolution of ϕ. The motion of ϕ is determined by the level set equation∂ϕ∂t=v/∇ϕ/,where v is the speed of propagation of Γ in the normal direction. In our numerical tests, we used the boundary curve of the region found by the Directional Ratio approach inside the soma as the initialization curve Γ of the level set evolution equation. We set the speed of propagation of Γ in the normal direction proportional to M − ∣∇(𝒟af)∣, where ∇(𝒟af) is the gradient of the Directional Ratio, pointing in the direction of the interior of the soma, and M is the maximum of the magnitude of the gradient of the Directional Ratio. This way, Γ evolves outwards, in the direction of the boundary of the segmented region (as shown in Fig. 2) and the velocity of evolution becomes slower and eventually stops when Γ reached the boundary of the segmented region. Note that, for our numerical implementation of the level set method, we have adapted the implementation of B. Sumengen [35] based on [33].


Automated detection of soma location and morphology in neuronal network cultures.

Ozcan B, Negi P, Laezza F, Papadakis M, Labate D - PLoS ONE (2015)

Application of level set method to detect soma area.The figure shows a detail from a segmented image of a neuron (MIP) where colors correspond to the values of the Directional Ratio values and range between 1 (=red) and 0 (=blue). The application of the threshold value 0.9 identifies a region strictly inside the soma, with boundary curve Γ (in the left panel). The level set method evolves the boundary curve Γ with a velocity in the normal direction (indicated by the arrows in the right panel) that depends on the magnitude of the gradient of the Directional Ratio.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4390318&req=5

pone.0121886.g002: Application of level set method to detect soma area.The figure shows a detail from a segmented image of a neuron (MIP) where colors correspond to the values of the Directional Ratio values and range between 1 (=red) and 0 (=blue). The application of the threshold value 0.9 identifies a region strictly inside the soma, with boundary curve Γ (in the left panel). The level set method evolves the boundary curve Γ with a velocity in the normal direction (indicated by the arrows in the right panel) that depends on the magnitude of the gradient of the Directional Ratio.
Mentions: Recall that the level set method is a variational approach introduced to track evolution of curves and shapes without having to parameterize these objects. The main idea is to identify a curve (or interface) Γ as the zero level set of a three-dimensional level set function ϕ and to follow the changes of Γ = {(x, y) : ϕ(x, y) = 0} from the evolution of ϕ. The motion of ϕ is determined by the level set equation∂ϕ∂t=v/∇ϕ/,where v is the speed of propagation of Γ in the normal direction. In our numerical tests, we used the boundary curve of the region found by the Directional Ratio approach inside the soma as the initialization curve Γ of the level set evolution equation. We set the speed of propagation of Γ in the normal direction proportional to M − ∣∇(𝒟af)∣, where ∇(𝒟af) is the gradient of the Directional Ratio, pointing in the direction of the interior of the soma, and M is the maximum of the magnitude of the gradient of the Directional Ratio. This way, Γ evolves outwards, in the direction of the boundary of the segmented region (as shown in Fig. 2) and the velocity of evolution becomes slower and eventually stops when Γ reached the boundary of the segmented region. Note that, for our numerical implementation of the level set method, we have adapted the implementation of B. Sumengen [35] based on [33].

Bottom Line: 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.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.

View Article: PubMed Central - PubMed

Affiliation: Dept. of Mathematics, University of Houston, Houston, Texas, United States of America.

ABSTRACT
Automated identification of the primary components of a neuron and extraction of its sub-cellular 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.

No MeSH data available.


Related in: MedlinePlus