Repository logo
 
Publication

Stacked Denoising Autoencoders and Transfer Learning for Immunogold Particles Detection and Recognition

2017-12-07Preprint Open access
Simple item page
dc.contributor.authorSousa, Ricardo
dc.contributor.authorSantos, Jorge M.
dc.contributor.authorSilva, Luís M.
dc.contributor.authorAlexandre, Luís
dc.contributor.authorEsteves, Tiago
dc.contributor.authorRocha, Sara
dc.contributor.authorMonjardino, Paulo
dc.contributor.authorSá, Joaquim Marques de
dc.contributor.authorFigueiredo, Francisco
dc.contributor.authorQuelhas, Pedro
dc.date.accessioned2020-01-13T10:13:15Z
dc.date.available2020-01-13T10:13:15Z
dc.date.issued2017-12-07
dc.description.abstractIn this paper we present a system for the detection of immunogold particles and a Transfer Learning (TL) framework for the recognition of these immunogold particles. Immunogold particles are part of a high-magnification method for the selective localization of biological molecules at the subcellular level only visible through Electron Microscopy. The number of immunogold particles in the cell walls allows the assessment of the differences in their compositions providing a tool to analise the quality of different plants. For its quantization one requires a laborious manual labeling (or annotation) of images containing hundreds of particles. The system that is proposed in this paper can leverage significantly the burden of this manual task. For particle detection we use a LoG filter coupled with a SDA. In order to improve the recognition, we also study the applicability of TL settings for immunogold recognition. TL reuses the learning model of a source problem on other datasets (target problems) containing particles of different sizes. The proposed system was developed to solve a particular problem on maize cells, namely to determine the composition of cell wall ingrowths in endosperm transfer cells. This novel dataset as well as the code for reproducing our experiments is made publicly available. We determined that the LoG detector alone attained more than 84\% of accuracy with the F-measure. Developing immunogold recognition with TL also provided superior performance when compared with the baseline models augmenting the accuracy rates by 10\%.pt_PT
dc.description.versioninfo:eu-repo/semantics/draftpt_PT
dc.identifier.urihttp://hdl.handle.net/10400.6/8236
dc.language.isoengpt_PT
dc.relationCELL MOTILITY AND MORPHOLOGY JOINT AUTOMATED ANALYSIS IN 2D AND 3D BIOLOGY ASSAYS
dc.relationBÚSQUEDA DE GENES COM EXPRESIÓN DIFERENCIAL EN LA GLÁNDULA MAMARIA OVINA
dc.subjectRecognitionpt_PT
dc.titleStacked Denoising Autoencoders and Transfer Learning for Immunogold Particles Detection and Recognitionpt_PT
dc.typepreprint
dspace.entity.typePublication
oaire.awardTitleCELL MOTILITY AND MORPHOLOGY JOINT AUTOMATED ANALYSIS IN 2D AND 3D BIOLOGY ASSAYS
oaire.awardTitleBÚSQUEDA DE GENES COM EXPRESIÓN DIFERENCIAL EN LA GLÁNDULA MAMARIA OVINA
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/COMPETE/PTDC%2FEIA-EIA%2F119004%2F2010/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FBIM%2F04293%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT//SFRH%2FBD%2F80508%2F2011/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT//SFRH%2FBD%2F8122%2F2002/PT
oaire.fundingStreamCOMPETE
oaire.fundingStream5876
person.familyNameFernandes dos Santos
person.familyNameAlexandre
person.familyNameMonjardino
person.givenNameJorge Manuel
person.givenNameLuís
person.givenNamePaulo
person.identifierR_1v6lsAAAAJ&hl
person.identifier.ciencia-id5316-E503-BDAF
person.identifier.ciencia-id2014-0F06-A3E3
person.identifier.ciencia-id6A14-2967-6B39
person.identifier.orcid0000-0002-2760-7756
person.identifier.orcid0000-0002-5133-5025
person.identifier.orcid0000-0003-2852-8467
person.identifier.ridE-8770-2013
person.identifier.scopus-author-id7402389359
person.identifier.scopus-author-id8847713100
person.identifier.scopus-author-id8669171500
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typepreprintpt_PT
relation.isAuthorOfPublication61a2ea2a-f3c3-4380-a946-63fe08e1e63e
relation.isAuthorOfPublication131ec6eb-b61a-4f27-953f-12e948a43a96
relation.isAuthorOfPublicatione99aea8a-bccd-4f33-89eb-7a6751046fe3
relation.isAuthorOfPublication.latestForDiscovery131ec6eb-b61a-4f27-953f-12e948a43a96
relation.isProjectOfPublicationf7117fb4-ecc4-41a1-90c7-91b13a621386
relation.isProjectOfPublication68ae0fac-96f3-417f-9191-6ab7ffca362a
relation.isProjectOfPublication57b58b38-a283-49af-8c76-3e0f1c2a4d2f
relation.isProjectOfPublication8d6d84a3-259b-44c3-bd87-70721b8a8c38
relation.isProjectOfPublication.latestForDiscovery68ae0fac-96f3-417f-9191-6ab7ffca362a

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1712.02824.pdf
Size:
2.77 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

FE - DI | Documentos por Auto-Depósito
ICI - IT-UBI | Documentos por Auto-Depósito