Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases

Abstract Tumor types are classically distinguished based on biopsies of the tumor itself, as well as a radiological interpretation using diverse MRI modalities. In the current study, the overarching goal is to demonstrate that primary (glioblastomas) and secondary (brain metastases) malignancies can...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zahra Riahi Samani, Drew Parker, Ronald Wolf, Wes Hodges, Steven Brem, Ragini Verma
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1139ecc47432450a89617a5380bdfd60
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1139ecc47432450a89617a5380bdfd60
record_format	dspace
spelling	oai:doaj.org-article:1139ecc47432450a89617a5380bdfd602021-12-02T16:08:08ZDistinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases10.1038/s41598-021-93804-62045-2322https://doaj.org/article/1139ecc47432450a89617a5380bdfd602021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93804-6https://doaj.org/toc/2045-2322Abstract Tumor types are classically distinguished based on biopsies of the tumor itself, as well as a radiological interpretation using diverse MRI modalities. In the current study, the overarching goal is to demonstrate that primary (glioblastomas) and secondary (brain metastases) malignancies can be differentiated based on the microstructure of the peritumoral region. This is achieved by exploiting the extracellular water differences between vasogenic edema and infiltrative tissue and training a convolutional neural network (CNN) on the Diffusion Tensor Imaging (DTI)-derived free water volume fraction. We obtained 85% accuracy in discriminating extracellular water differences between local patches in the peritumoral area of 66 glioblastomas and 40 metastatic patients in a cross-validation setting. On an independent test cohort consisting of 20 glioblastomas and 10 metastases, we got 93% accuracy in discriminating metastases from glioblastomas using majority voting on patches. This level of accuracy surpasses CNNs trained on other conventional DTI-based measures such as fractional anisotropy (FA) and mean diffusivity (MD), that have been used in other studies. Additionally, the CNN captures the peritumoral heterogeneity better than conventional texture features, including Gabor and radiomic features. Our results demonstrate that the extracellular water content of the peritumoral tissue, as captured by the free water volume fraction, is best able to characterize the differences between infiltrative and vasogenic peritumoral regions, paving the way for its use in classifying and benchmarking peritumoral tissue with varying degrees of infiltration.Zahra Riahi SamaniDrew ParkerRonald WolfWes HodgesSteven BremRagini VermaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Zahra Riahi Samani Drew Parker Ronald Wolf Wes Hodges Steven Brem Ragini Verma Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
description	Abstract Tumor types are classically distinguished based on biopsies of the tumor itself, as well as a radiological interpretation using diverse MRI modalities. In the current study, the overarching goal is to demonstrate that primary (glioblastomas) and secondary (brain metastases) malignancies can be differentiated based on the microstructure of the peritumoral region. This is achieved by exploiting the extracellular water differences between vasogenic edema and infiltrative tissue and training a convolutional neural network (CNN) on the Diffusion Tensor Imaging (DTI)-derived free water volume fraction. We obtained 85% accuracy in discriminating extracellular water differences between local patches in the peritumoral area of 66 glioblastomas and 40 metastatic patients in a cross-validation setting. On an independent test cohort consisting of 20 glioblastomas and 10 metastases, we got 93% accuracy in discriminating metastases from glioblastomas using majority voting on patches. This level of accuracy surpasses CNNs trained on other conventional DTI-based measures such as fractional anisotropy (FA) and mean diffusivity (MD), that have been used in other studies. Additionally, the CNN captures the peritumoral heterogeneity better than conventional texture features, including Gabor and radiomic features. Our results demonstrate that the extracellular water content of the peritumoral tissue, as captured by the free water volume fraction, is best able to characterize the differences between infiltrative and vasogenic peritumoral regions, paving the way for its use in classifying and benchmarking peritumoral tissue with varying degrees of infiltration.
format	article
author	Zahra Riahi Samani Drew Parker Ronald Wolf Wes Hodges Steven Brem Ragini Verma
author_facet	Zahra Riahi Samani Drew Parker Ronald Wolf Wes Hodges Steven Brem Ragini Verma
author_sort	Zahra Riahi Samani
title	Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
title_short	Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
title_full	Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
title_fullStr	Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
title_full_unstemmed	Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
title_sort	distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1139ecc47432450a89617a5380bdfd60
work_keys_str_mv	AT zahrariahisamani distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases AT drewparker distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases AT ronaldwolf distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases AT weshodges distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases AT stevenbrem distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases AT raginiverma distincttumorsignaturesusingdeeplearningbasedcharacterizationoftheperitumoralmicroenvironmentinglioblastomasandbrainmetastases
_version_	1718384576772964352

Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases

Ejemplares similares