A Manual Segmentation Tool for Three-Dimensional Neuron Datasets
To date, automated or semi-automated software and algorithms for segmentation of neurons from three-dimensional imaging datasets have had limited success. The gold standard for neural segmentation is considered to be the manual isolation performed by an expert. To facilitate the manual isolation of...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2017-05-01
|
Series: | Frontiers in Neuroinformatics |
Subjects: | |
Online Access: | http://journal.frontiersin.org/article/10.3389/fninf.2017.00036/full |
id |
doaj-9d9eba3c9e4c4d148ad9be4bdcea17c7 |
---|---|
record_format |
Article |
spelling |
doaj-9d9eba3c9e4c4d148ad9be4bdcea17c72020-11-25T00:19:09ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962017-05-011110.3389/fninf.2017.00036253843A Manual Segmentation Tool for Three-Dimensional Neuron DatasetsChiara Magliaro0Alejandro L. Callara1Alejandro L. Callara2Nicola Vanello3Nicola Vanello4Arti Ahluwalia5Arti Ahluwalia6Centro di Ricerca “E. Piaggio”, Università di PisaPisa, ItalyCentro di Ricerca “E. Piaggio”, Università di PisaPisa, ItalyDipartimento di Ingegneria dell'Informazione, Università di PisaPisa, ItalyCentro di Ricerca “E. Piaggio”, Università di PisaPisa, ItalyDipartimento di Ingegneria dell'Informazione, Università di PisaPisa, ItalyCentro di Ricerca “E. Piaggio”, Università di PisaPisa, ItalyDipartimento di Ingegneria dell'Informazione, Università di PisaPisa, ItalyTo date, automated or semi-automated software and algorithms for segmentation of neurons from three-dimensional imaging datasets have had limited success. The gold standard for neural segmentation is considered to be the manual isolation performed by an expert. To facilitate the manual isolation of complex objects from image stacks, such as neurons in their native arrangement within the brain, a new Manual Segmentation Tool (ManSegTool) has been developed. ManSegTool allows user to load an image stack, scroll down the images and to manually draw the structures of interest stack-by-stack. Users can eliminate unwanted regions or split structures (i.e., branches from different neurons that are too close each other, but, to the experienced eye, clearly belong to a unique cell), to view the object in 3D and save the results obtained. The tool can be used for testing the performance of a single-neuron segmentation algorithm or to extract complex objects, where the available automated methods still fail. Here we describe the software's main features and then show an example of how ManSegTool can be used to segment neuron images acquired using a confocal microscope. In particular, expert neuroscientists were asked to segment different neurons from which morphometric variables were subsequently extracted as a benchmark for precision. In addition, a literature-defined index for evaluating the goodness of segmentation was used as a benchmark for accuracy. Neocortical layer axons from a DIADEM challenge dataset were also segmented with ManSegTool and compared with the manual “gold-standard” generated for the competition.http://journal.frontiersin.org/article/10.3389/fninf.2017.00036/fullmanual segmentationconfocal stacksCLARITYneuronsL7GFPsegmentation goodness |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chiara Magliaro Alejandro L. Callara Alejandro L. Callara Nicola Vanello Nicola Vanello Arti Ahluwalia Arti Ahluwalia |
spellingShingle |
Chiara Magliaro Alejandro L. Callara Alejandro L. Callara Nicola Vanello Nicola Vanello Arti Ahluwalia Arti Ahluwalia A Manual Segmentation Tool for Three-Dimensional Neuron Datasets Frontiers in Neuroinformatics manual segmentation confocal stacks CLARITY neurons L7GFP segmentation goodness |
author_facet |
Chiara Magliaro Alejandro L. Callara Alejandro L. Callara Nicola Vanello Nicola Vanello Arti Ahluwalia Arti Ahluwalia |
author_sort |
Chiara Magliaro |
title |
A Manual Segmentation Tool for Three-Dimensional Neuron Datasets |
title_short |
A Manual Segmentation Tool for Three-Dimensional Neuron Datasets |
title_full |
A Manual Segmentation Tool for Three-Dimensional Neuron Datasets |
title_fullStr |
A Manual Segmentation Tool for Three-Dimensional Neuron Datasets |
title_full_unstemmed |
A Manual Segmentation Tool for Three-Dimensional Neuron Datasets |
title_sort |
manual segmentation tool for three-dimensional neuron datasets |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroinformatics |
issn |
1662-5196 |
publishDate |
2017-05-01 |
description |
To date, automated or semi-automated software and algorithms for segmentation of neurons from three-dimensional imaging datasets have had limited success. The gold standard for neural segmentation is considered to be the manual isolation performed by an expert. To facilitate the manual isolation of complex objects from image stacks, such as neurons in their native arrangement within the brain, a new Manual Segmentation Tool (ManSegTool) has been developed. ManSegTool allows user to load an image stack, scroll down the images and to manually draw the structures of interest stack-by-stack. Users can eliminate unwanted regions or split structures (i.e., branches from different neurons that are too close each other, but, to the experienced eye, clearly belong to a unique cell), to view the object in 3D and save the results obtained. The tool can be used for testing the performance of a single-neuron segmentation algorithm or to extract complex objects, where the available automated methods still fail. Here we describe the software's main features and then show an example of how ManSegTool can be used to segment neuron images acquired using a confocal microscope. In particular, expert neuroscientists were asked to segment different neurons from which morphometric variables were subsequently extracted as a benchmark for precision. In addition, a literature-defined index for evaluating the goodness of segmentation was used as a benchmark for accuracy. Neocortical layer axons from a DIADEM challenge dataset were also segmented with ManSegTool and compared with the manual “gold-standard” generated for the competition. |
topic |
manual segmentation confocal stacks CLARITY neurons L7GFP segmentation goodness |
url |
http://journal.frontiersin.org/article/10.3389/fninf.2017.00036/full |
work_keys_str_mv |
AT chiaramagliaro amanualsegmentationtoolforthreedimensionalneurondatasets AT alejandrolcallara amanualsegmentationtoolforthreedimensionalneurondatasets AT alejandrolcallara amanualsegmentationtoolforthreedimensionalneurondatasets AT nicolavanello amanualsegmentationtoolforthreedimensionalneurondatasets AT nicolavanello amanualsegmentationtoolforthreedimensionalneurondatasets AT artiahluwalia amanualsegmentationtoolforthreedimensionalneurondatasets AT artiahluwalia amanualsegmentationtoolforthreedimensionalneurondatasets AT chiaramagliaro manualsegmentationtoolforthreedimensionalneurondatasets AT alejandrolcallara manualsegmentationtoolforthreedimensionalneurondatasets AT alejandrolcallara manualsegmentationtoolforthreedimensionalneurondatasets AT nicolavanello manualsegmentationtoolforthreedimensionalneurondatasets AT nicolavanello manualsegmentationtoolforthreedimensionalneurondatasets AT artiahluwalia manualsegmentationtoolforthreedimensionalneurondatasets AT artiahluwalia manualsegmentationtoolforthreedimensionalneurondatasets |
_version_ |
1725372956893249536 |