Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type

Abstract Generative adversarial network (GAN) creates synthetic images to increase data quantity, but whether GAN ensures meaningful morphologic variations is still unknown. We investigated whether GAN-based synthetic images provide sufficient morphologic variations to improve molecular-based predic...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ji Eun Park, Dain Eun, Ho Sung Kim, Da Hyun Lee, Ryoung Woo Jang, Namkug Kim
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/b9e0f4185fc740d6af0b446f7f57164e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b9e0f4185fc740d6af0b446f7f57164e
record_format dspace
spelling oai:doaj.org-article:b9e0f4185fc740d6af0b446f7f57164e2021-12-02T15:36:13ZGenerative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type10.1038/s41598-021-89477-w2045-2322https://doaj.org/article/b9e0f4185fc740d6af0b446f7f57164e2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-89477-whttps://doaj.org/toc/2045-2322Abstract Generative adversarial network (GAN) creates synthetic images to increase data quantity, but whether GAN ensures meaningful morphologic variations is still unknown. We investigated whether GAN-based synthetic images provide sufficient morphologic variations to improve molecular-based prediction, as a rare disease of isocitrate dehydrogenase (IDH)-mutant glioblastomas. GAN was initially trained on 500 normal brains and 110 IDH-mutant high-grade astocytomas, and paired contrast-enhanced T1-weighted and FLAIR MRI data were generated. Diagnostic models were developed from real IDH-wild type (n = 80) with real IDH-mutant glioblastomas (n = 38), or with synthetic IDH-mutant glioblastomas, or augmented by adding both real and synthetic IDH-mutant glioblastomas. Turing tests showed synthetic data showed reality (classification rate of 55%). Both the real and synthetic data showed that a more frontal or insular location (odds ratio [OR] 1.34 vs. 1.52; P = 0.04) and distinct non-enhancing tumor margins (OR 2.68 vs. 3.88; P < 0.001), which become significant predictors of IDH-mutation. In an independent validation set, diagnostic accuracy was higher for the augmented model (90.9% [40/44] and 93.2% [41/44] for each reader, respectively) than for the real model (84.1% [37/44] and 86.4% [38/44] for each reader, respectively). The GAN-based synthetic images yield morphologically variable, realistic-seeming IDH-mutant glioblastomas. GAN will be useful to create a realistic training set in terms of morphologic variations and quality, thereby improving diagnostic performance in a clinical model.Ji Eun ParkDain EunHo Sung KimDa Hyun LeeRyoung Woo JangNamkug KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Ji Eun Park
Dain Eun
Ho Sung Kim
Da Hyun Lee
Ryoung Woo Jang
Namkug Kim
Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
description Abstract Generative adversarial network (GAN) creates synthetic images to increase data quantity, but whether GAN ensures meaningful morphologic variations is still unknown. We investigated whether GAN-based synthetic images provide sufficient morphologic variations to improve molecular-based prediction, as a rare disease of isocitrate dehydrogenase (IDH)-mutant glioblastomas. GAN was initially trained on 500 normal brains and 110 IDH-mutant high-grade astocytomas, and paired contrast-enhanced T1-weighted and FLAIR MRI data were generated. Diagnostic models were developed from real IDH-wild type (n = 80) with real IDH-mutant glioblastomas (n = 38), or with synthetic IDH-mutant glioblastomas, or augmented by adding both real and synthetic IDH-mutant glioblastomas. Turing tests showed synthetic data showed reality (classification rate of 55%). Both the real and synthetic data showed that a more frontal or insular location (odds ratio [OR] 1.34 vs. 1.52; P = 0.04) and distinct non-enhancing tumor margins (OR 2.68 vs. 3.88; P < 0.001), which become significant predictors of IDH-mutation. In an independent validation set, diagnostic accuracy was higher for the augmented model (90.9% [40/44] and 93.2% [41/44] for each reader, respectively) than for the real model (84.1% [37/44] and 86.4% [38/44] for each reader, respectively). The GAN-based synthetic images yield morphologically variable, realistic-seeming IDH-mutant glioblastomas. GAN will be useful to create a realistic training set in terms of morphologic variations and quality, thereby improving diagnostic performance in a clinical model.
format article
author Ji Eun Park
Dain Eun
Ho Sung Kim
Da Hyun Lee
Ryoung Woo Jang
Namkug Kim
author_facet Ji Eun Park
Dain Eun
Ho Sung Kim
Da Hyun Lee
Ryoung Woo Jang
Namkug Kim
author_sort Ji Eun Park
title Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
title_short Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
title_full Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
title_fullStr Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
title_full_unstemmed Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
title_sort generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/b9e0f4185fc740d6af0b446f7f57164e
work_keys_str_mv AT jieunpark generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
AT daineun generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
AT hosungkim generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
AT dahyunlee generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
AT ryoungwoojang generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
AT namkugkim generativeadversarialnetworkforglioblastomaensuresmorphologicvariationsandimprovesdiagnosticmodelforisocitratedehydrogenasemutanttype
_version_ 1718386377206267904