Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation

Abstract Current image processing methods for dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) do not capture complex dynamic information of time-signal intensity curves. We investigated whether an autoencoder-based pattern analysis of DSC MRI captured representative temporal f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ji Eun Park, Ho Sung Kim, Junkyu Lee, E.-Nae Cheong, Ilah Shin, Sung Soo Ahn, Woo Hyun Shim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6aac4ed3f8ab4abebaa6c94e37576693
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6aac4ed3f8ab4abebaa6c94e37576693
record_format	dspace
spelling	oai:doaj.org-article:6aac4ed3f8ab4abebaa6c94e375766932021-12-02T11:43:36ZDeep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation10.1038/s41598-020-78485-x2045-2322https://doaj.org/article/6aac4ed3f8ab4abebaa6c94e375766932020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78485-xhttps://doaj.org/toc/2045-2322Abstract Current image processing methods for dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) do not capture complex dynamic information of time-signal intensity curves. We investigated whether an autoencoder-based pattern analysis of DSC MRI captured representative temporal features that improves tissue characterization and tumor diagnosis in a multicenter setting. The autoencoder was applied to the time-signal intensity curves to obtain representative temporal patterns, which were subsequently learned by a convolutional neural network. This network was trained with 216 preoperative DSC MRI acquisitions and validated using external data (n = 43) collected with different DSC acquisition protocols. The autoencoder applied to time-signal intensity curves and clustering obtained nine representative clusters of temporal patterns, which accurately identified tumor and non-tumoral tissues. The dominant clusters of temporal patterns distinguished primary central nervous system lymphoma (PCNSL) from glioblastoma (AUC 0.89) and metastasis from glioblastoma (AUC 0.95). The autoencoder captured DSC time-signal intensity patterns that improved identification of tumoral tissues and differentiation of tumor type and was generalizable across centers.Ji Eun ParkHo Sung KimJunkyu LeeE.-Nae CheongIlah ShinSung Soo AhnWoo Hyun ShimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ji Eun Park Ho Sung Kim Junkyu Lee E.-Nae Cheong Ilah Shin Sung Soo Ahn Woo Hyun Shim Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
description	Abstract Current image processing methods for dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) do not capture complex dynamic information of time-signal intensity curves. We investigated whether an autoencoder-based pattern analysis of DSC MRI captured representative temporal features that improves tissue characterization and tumor diagnosis in a multicenter setting. The autoencoder was applied to the time-signal intensity curves to obtain representative temporal patterns, which were subsequently learned by a convolutional neural network. This network was trained with 216 preoperative DSC MRI acquisitions and validated using external data (n = 43) collected with different DSC acquisition protocols. The autoencoder applied to time-signal intensity curves and clustering obtained nine representative clusters of temporal patterns, which accurately identified tumor and non-tumoral tissues. The dominant clusters of temporal patterns distinguished primary central nervous system lymphoma (PCNSL) from glioblastoma (AUC 0.89) and metastasis from glioblastoma (AUC 0.95). The autoencoder captured DSC time-signal intensity patterns that improved identification of tumoral tissues and differentiation of tumor type and was generalizable across centers.
format	article
author	Ji Eun Park Ho Sung Kim Junkyu Lee E.-Nae Cheong Ilah Shin Sung Soo Ahn Woo Hyun Shim
author_facet	Ji Eun Park Ho Sung Kim Junkyu Lee E.-Nae Cheong Ilah Shin Sung Soo Ahn Woo Hyun Shim
author_sort	Ji Eun Park
title	Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
title_short	Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
title_full	Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
title_fullStr	Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
title_full_unstemmed	Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
title_sort	deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/6aac4ed3f8ab4abebaa6c94e37576693
work_keys_str_mv	AT jieunpark deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT hosungkim deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT junkyulee deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT enaecheong deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT ilahshin deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT sungsooahn deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation AT woohyunshim deeplearnedtimesignalintensitypatternanalysisusinganautoencodercapturesmagneticresonanceperfusionheterogeneityforbraintumordifferentiation
_version_	1718395347454132224

Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation

Ejemplares similares