Abdominal MRI synthesis using styleGAN2-ADA

Detalhes bibliográficos
Autor(a) principal: Gonçalves, Bernardo
Data de Publicação: 2023
Outros Autores: Vieira, Pedro, Vieira, Ana
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.21/16750
Resumo: This work was funded by FCT—Portuguese Foundation for Science and Technology and Bee2Fire SA under the PhD grant with reference PD/BDE/150624/2020.
id RCAP_dd796ee1af193b98a8eadb93b57df34a
oai_identifier_str oai:repositorio.ipl.pt:10400.21/16750
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Abdominal MRI synthesis using styleGAN2-ADAMagnetic resonance imagingGenerative adversarial networksStyleGAN2Image synthesisMedical imagingDeep learningMalignant tumourPipelinesTraining dataThis work was funded by FCT—Portuguese Foundation for Science and Technology and Bee2Fire SA under the PhD grant with reference PD/BDE/150624/2020.The lack of labeled medical data still poses one of the biggest issues when creating Deep Learning models in the medical field. Modern data augmentation techniques like the generation of synthetic images have gained a special interest. In recent years there has been a significant improvement in GANs. StyleGAN2 achieves impressive results in the generation of natural images. StyleGAN2-ADA was created to respond to the lack of training data when training an image synthesis model, which is very frequent in the medical field. Some works used styleGAN to generate melanomas, breast cancer histological images, and MR and CT images. In this work, we apply, for the first time, a styleGAN2-ADA to a small dataset of abdominal MRI with 1.3k images. From the augmentation pipeline created by the authors of styleGAN2-ADA, we removed all augmentations except the geometric transformations and pixel blitting operations. We trained our network for 70 hours. Our generated dataset has a precision score of 59,33 % and a FID score of 18,14. We conclude that the styleGAN2-ADA is a viable solution to generate MRI using a small dataset.IEEERCIPLGonçalves, BernardoVieira, PedroVieira, Ana2023-072023-07-01T00:00:00Z2025-07-31T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.21/16750engGonçalves B, Vieira P, Vieira A (Ana). Abdominal MRI synthesis using styleGAN2-ADA. In: 2023 IST-Africa Conference (IST-Africa), Tshwane (South Africa), May 31 – June 02, 2023.10.23919/IST-Africa60249.2023.10187755info:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-01-10T02:18:23Zoai:repositorio.ipl.pt:10400.21/16750Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:31:12.453697Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Abdominal MRI synthesis using styleGAN2-ADA
title Abdominal MRI synthesis using styleGAN2-ADA
spellingShingle Abdominal MRI synthesis using styleGAN2-ADA
Gonçalves, Bernardo
Magnetic resonance imaging
Generative adversarial networks
StyleGAN2
Image synthesis
Medical imaging
Deep learning
Malignant tumour
Pipelines
Training data
title_short Abdominal MRI synthesis using styleGAN2-ADA
title_full Abdominal MRI synthesis using styleGAN2-ADA
title_fullStr Abdominal MRI synthesis using styleGAN2-ADA
title_full_unstemmed Abdominal MRI synthesis using styleGAN2-ADA
title_sort Abdominal MRI synthesis using styleGAN2-ADA
author Gonçalves, Bernardo
author_facet Gonçalves, Bernardo
Vieira, Pedro
Vieira, Ana
author_role author
author2 Vieira, Pedro
Vieira, Ana
author2_role author
author
dc.contributor.none.fl_str_mv RCIPL
dc.contributor.author.fl_str_mv Gonçalves, Bernardo
Vieira, Pedro
Vieira, Ana
dc.subject.por.fl_str_mv Magnetic resonance imaging
Generative adversarial networks
StyleGAN2
Image synthesis
Medical imaging
Deep learning
Malignant tumour
Pipelines
Training data
topic Magnetic resonance imaging
Generative adversarial networks
StyleGAN2
Image synthesis
Medical imaging
Deep learning
Malignant tumour
Pipelines
Training data
description This work was funded by FCT—Portuguese Foundation for Science and Technology and Bee2Fire SA under the PhD grant with reference PD/BDE/150624/2020.
publishDate 2023
dc.date.none.fl_str_mv 2023-07
2023-07-01T00:00:00Z
2025-07-31T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.21/16750
url http://hdl.handle.net/10400.21/16750
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Gonçalves B, Vieira P, Vieira A (Ana). Abdominal MRI synthesis using styleGAN2-ADA. In: 2023 IST-Africa Conference (IST-Africa), Tshwane (South Africa), May 31 – June 02, 2023.
10.23919/IST-Africa60249.2023.10187755
dc.rights.driver.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799136793841369088

Registros relacionados