Improving skeleton algorithm for helping Caenorhabditis elegans trackers
Abstract One of the main problems when monitoring Caenorhabditis elegans nematodes (C. elegans) is tracking their poses by automatic computer vision systems. This is a challenge given the marked flexibility that their bodies present and the different poses that can be performed during their behaviou...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2020-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-020-79430-8 |
id |
doaj-7ca02d51b7274697bf7065ac3244e2a6 |
---|---|
record_format |
Article |
spelling |
doaj-7ca02d51b7274697bf7065ac3244e2a62020-12-20T12:32:59ZengNature Publishing GroupScientific Reports2045-23222020-12-0110111210.1038/s41598-020-79430-8Improving skeleton algorithm for helping Caenorhabditis elegans trackersPablo E. Layana Castro0Joan Carles Puchalt1Antonio-José Sánchez-Salmerón2Instituto de Automática e Informática Industrial, Universitat Politècnica de ValènciaInstituto de Automática e Informática Industrial, Universitat Politècnica de ValènciaInstituto de Automática e Informática Industrial, Universitat Politècnica de ValènciaAbstract One of the main problems when monitoring Caenorhabditis elegans nematodes (C. elegans) is tracking their poses by automatic computer vision systems. This is a challenge given the marked flexibility that their bodies present and the different poses that can be performed during their behaviour individually, which become even more complicated when worms aggregate with others while moving. This work proposes a simple solution by combining some computer vision techniques to help to determine certain worm poses and to identify each one during aggregation or in coiled shapes. This new method is based on the distance transformation function to obtain better worm skeletons. Experiments were performed with 205 plates, each with 10, 15, 30, 60 or 100 worms, which totals 100,000 worm poses approximately. A comparison of the proposed method was made to a classic skeletonisation method to find that 2196 problematic poses had improved by between 22% and 1% on average in the pose predictions of each worm.https://doi.org/10.1038/s41598-020-79430-8 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Pablo E. Layana Castro Joan Carles Puchalt Antonio-José Sánchez-Salmerón |
spellingShingle |
Pablo E. Layana Castro Joan Carles Puchalt Antonio-José Sánchez-Salmerón Improving skeleton algorithm for helping Caenorhabditis elegans trackers Scientific Reports |
author_facet |
Pablo E. Layana Castro Joan Carles Puchalt Antonio-José Sánchez-Salmerón |
author_sort |
Pablo E. Layana Castro |
title |
Improving skeleton algorithm for helping Caenorhabditis elegans trackers |
title_short |
Improving skeleton algorithm for helping Caenorhabditis elegans trackers |
title_full |
Improving skeleton algorithm for helping Caenorhabditis elegans trackers |
title_fullStr |
Improving skeleton algorithm for helping Caenorhabditis elegans trackers |
title_full_unstemmed |
Improving skeleton algorithm for helping Caenorhabditis elegans trackers |
title_sort |
improving skeleton algorithm for helping caenorhabditis elegans trackers |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2020-12-01 |
description |
Abstract One of the main problems when monitoring Caenorhabditis elegans nematodes (C. elegans) is tracking their poses by automatic computer vision systems. This is a challenge given the marked flexibility that their bodies present and the different poses that can be performed during their behaviour individually, which become even more complicated when worms aggregate with others while moving. This work proposes a simple solution by combining some computer vision techniques to help to determine certain worm poses and to identify each one during aggregation or in coiled shapes. This new method is based on the distance transformation function to obtain better worm skeletons. Experiments were performed with 205 plates, each with 10, 15, 30, 60 or 100 worms, which totals 100,000 worm poses approximately. A comparison of the proposed method was made to a classic skeletonisation method to find that 2196 problematic poses had improved by between 22% and 1% on average in the pose predictions of each worm. |
url |
https://doi.org/10.1038/s41598-020-79430-8 |
work_keys_str_mv |
AT pabloelayanacastro improvingskeletonalgorithmforhelpingcaenorhabditiseleganstrackers AT joancarlespuchalt improvingskeletonalgorithmforhelpingcaenorhabditiseleganstrackers AT antoniojosesanchezsalmeron improvingskeletonalgorithmforhelpingcaenorhabditiseleganstrackers |
_version_ |
1724376496506667008 |