Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

Abstract Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created...

Description complète

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sajith Kecheril Sadanandan, Petter Ranefall, Sylvie Le Guyader, Carolina Wählby
Format:	article
Langue:	EN
Publié:	Nature Portfolio 2017
Sujets:	Medicine R Science Q
Accès en ligne:	https://doaj.org/article/a09dea75f9f64b2fb9d607e6e7bf0857
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

id	oai:doaj.org-article:a09dea75f9f64b2fb9d607e6e7bf0857
record_format	dspace
spelling	oai:doaj.org-article:a09dea75f9f64b2fb9d607e6e7bf08572021-12-02T16:06:20ZAutomated Training of Deep Convolutional Neural Networks for Cell Segmentation10.1038/s41598-017-07599-62045-2322https://doaj.org/article/a09dea75f9f64b2fb9d607e6e7bf08572017-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-07599-6https://doaj.org/toc/2045-2322Abstract Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.Sajith Kecheril SadanandanPetter RanefallSylvie Le GuyaderCarolina WählbyNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-7 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sajith Kecheril Sadanandan Petter Ranefall Sylvie Le Guyader Carolina Wählby Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
description	Abstract Deep Convolutional Neural Networks (DCNN) have recently emerged as superior for many image segmentation tasks. The DCNN performance is however heavily dependent on the availability of large amounts of problem-specific training samples. Here we show that DCNNs trained on ground truth created automatically using fluorescently labeled cells, perform similar to manual annotations.
format	article
author	Sajith Kecheril Sadanandan Petter Ranefall Sylvie Le Guyader Carolina Wählby
author_facet	Sajith Kecheril Sadanandan Petter Ranefall Sylvie Le Guyader Carolina Wählby
author_sort	Sajith Kecheril Sadanandan
title	Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
title_short	Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
title_full	Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
title_fullStr	Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
title_full_unstemmed	Automated Training of Deep Convolutional Neural Networks for Cell Segmentation
title_sort	automated training of deep convolutional neural networks for cell segmentation
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/a09dea75f9f64b2fb9d607e6e7bf0857
work_keys_str_mv	AT sajithkecherilsadanandan automatedtrainingofdeepconvolutionalneuralnetworksforcellsegmentation AT petterranefall automatedtrainingofdeepconvolutionalneuralnetworksforcellsegmentation AT sylvieleguyader automatedtrainingofdeepconvolutionalneuralnetworksforcellsegmentation AT carolinawahlby automatedtrainingofdeepconvolutionalneuralnetworksforcellsegmentation
_version_	1718385042785304576

Automated Training of Deep Convolutional Neural Networks for Cell Segmentation

Documents similaires