Repository logo
 
Publication

Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets

2023-08-31Journal article Open access
Simple item page
dc.contributor.authorSpolaôr, Newton
dc.contributor.authorLee, Huei Diana
dc.contributor.authorMendes, Ana Isabel
dc.contributor.authorNogueira, Conceição
dc.contributor.authorParmezan, Antonio Rafael Sabino
dc.contributor.authorTakaki, Weber Shoity Resende
dc.contributor.authorCoy, Claudio Saddy Rodrigues
dc.contributor.authorWu, Feng Chung
dc.contributor.authorFonseca-Pinto, Rui
dc.date.accessioned2024-01-05T18:07:05Z
dc.date.available2024-01-05T18:07:05Z
dc.date.issued2023-08-31
dc.descriptionFunding We would like to acknowledge eurekaSD: Enhancing University Research and Education in Areas Useful for Sustainable Development - grants EK14AC0037 and EK15AC0264. We thank Araucária Foundation for the Support of the Scientific and Technological Development of Paraná through a Research and Technological Productivity Scholarship for H. D. Lee (grant 028/2019). We also thank the Brazilian National Council for Scientific and Technological Development (CNPq) through the grant number 142050/2019-9 for A. R. S. Parmezan. The Portuguese team was partially supported by Fundação para a Ciência e a Tecnologia (FCT). R. Fonseca-Pinto was financed by the projects UIDB/50008/2020, UIDP/50008/2020, UIDB/05704/2020 and UIDP/05704/2020 and C. V. Nogueira was financed by the projects UIDB/00013/2020 and UIDP/00013/2020. The funding agencies did not have any further involvement in this paper.pt_PT
dc.description.abstractConvolutional neural networks have been effective in several applications, arising as a promising supporting tool in a relevant Dermatology problem: skin cancer diagnosis. However, generalizing well can be difficult when little training data is available. The fine-tuning transfer learning strategy has been employed to differentiate properly malignant from non-malignant lesions in dermoscopic images. Fine-tuning a pre-trained network allows one to classify data in the target domain, occasionally with few images, using knowledge acquired in another domain. This work proposes eight fine-tuning settings based on convolutional networks previously trained on ImageNet that can be employed mainly in limited data samples to reduce overfitting risk. They differ on the architecture, the learning rate and the number of unfrozen layer blocks. We evaluated the settings in two public datasets with 104 and 200 dermoscopic images. By finding competitive configurations in small datasets, this paper illustrates that deep learning can be effective if one has only a few dozen malignant and non-malignant lesion images to study and differentiate in Dermatology. The proposal is also flexible and potentially useful for other domains. In fact, it performed satisfactorily in an assessment conducted in a larger dataset with 746 computerized tomographic images associated with the coronavirus disease.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationSpolaôr, N., Lee, H.D., Mendes, A.I. et al. Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets. Multimed Tools Appl (2023). https://doi.org/10.1007/s11042-023-16529-wpt_PT
dc.identifier.doihttps://doi.org/10.1007/s11042-023-16529-wpt_PT
dc.identifier.eissn1573-7721
dc.identifier.issn1380-7501
dc.identifier.urihttp://hdl.handle.net/10400.8/9194
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherSpringerpt_PT
dc.relationInstituto de Telecomunicações
dc.relationInstituto de Telecomunicações
dc.relationCenter for Innovative Care and Health Technology
dc.relationCenter for Innovative Care and Health Technology
dc.relationCenter of Mathematics of the University of Minho
dc.relationCenter of Mathematics of the University of Minho
dc.relation.publisherversionhttps://link.springer.com/article/10.1007/s11042-023-16529-wpt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectFeature learningpt_PT
dc.subjectFew-shot learningpt_PT
dc.subjectRMSproppt_PT
dc.subjectShallow learningpt_PT
dc.subjectStatistical testpt_PT
dc.subjectVGGpt_PT
dc.titleFine-tuning pre-trained neural networks for medical image classification in small clinical datasetspt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstituto de Telecomunicações
oaire.awardTitleInstituto de Telecomunicações
oaire.awardTitleCenter for Innovative Care and Health Technology
oaire.awardTitleCenter for Innovative Care and Health Technology
oaire.awardTitleCenter of Mathematics of the University of Minho
oaire.awardTitleCenter of Mathematics of the University of Minho
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50008%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F50008%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05704%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F05704%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00013%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F00013%2F2020/PT
oaire.citation.titleMultimedia Tools and Applicationspt_PT
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
person.familyNameNogueira
person.familyNameFonseca-Pinto
person.givenNameConceição
person.givenNameRui
person.identifier.ciencia-id9C14-CD1D-1298
person.identifier.ciencia-id681D-C547-B184
person.identifier.orcid0000-0002-9269-2221
person.identifier.orcid0000-0001-6774-5363
person.identifier.ridK-9449-2014
person.identifier.scopus-author-id24339135500
person.identifier.scopus-author-id26039086400
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.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
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationb44ae8f7-d99a-4098-ae0b-bbf22db8f2a0
relation.isAuthorOfPublication7eb9d123-1800-4afd-a2f6-91043353011b
relation.isAuthorOfPublication.latestForDiscoveryb44ae8f7-d99a-4098-ae0b-bbf22db8f2a0
relation.isProjectOfPublication0836c6a6-afd0-499e-8a16-612dd27ec1dc
relation.isProjectOfPublication91a8e212-cbb0-462f-b533-5ed3552e8067
relation.isProjectOfPublicationd421b07d-3471-4026-aa43-def80b8e142b
relation.isProjectOfPublicatione5ceb42e-60fb-425d-8576-b213fc64081f
relation.isProjectOfPublication18038fc5-694e-44e4-a3c2-9a83456c1612
relation.isProjectOfPublicationdc871795-a025-40ae-a1a2-cce1eedb2aff
relation.isProjectOfPublication.latestForDiscovery18038fc5-694e-44e4-a3c2-9a83456c1612

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s11042-023-16529-w.pdf
Size:
1.38 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ciTechCare - Artigos