Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study

Glioblastoma may appear similar to cerebral metastasis on conventional MRI in some cases, but their therapies differ significantly. This prospective feasibility study was aimed at differentiating them by applying the quantitative susceptibility mapping and quantitative blood-oxygen-level-dependent (...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hakim Baazaoui, Simon Hubertus, Máté E. Maros, Sherif A. Mohamed, Alex Förster, Lothar R. Schad, Holger Wenz
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	brain metastasis glioblastoma machine learning oxygenation tumor infiltration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/4b5856c301b04c5784719615773daec1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4b5856c301b04c5784719615773daec1
record_format	dspace
spelling	oai:doaj.org-article:4b5856c301b04c5784719615773daec12021-11-11T15:01:28ZArtificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study10.3390/app112199282076-3417https://doaj.org/article/4b5856c301b04c5784719615773daec12021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9928https://doaj.org/toc/2076-3417Glioblastoma may appear similar to cerebral metastasis on conventional MRI in some cases, but their therapies differ significantly. This prospective feasibility study was aimed at differentiating them by applying the quantitative susceptibility mapping and quantitative blood-oxygen-level-dependent (QSM + qBOLD) model to these entities for the first time. We prospectively included 15 untreated patients with glioblastoma (n = 7, median age: 68 years, range: 54–84 years) or brain metastasis (n = 8, median age 66 years, range: 50–78 years) who underwent preoperative MRI including multi-gradient echo and arterial spin labeling sequences. Oxygen extraction fraction (OEF), cerebral blood flow (CBF) and cerebral metabolic rate of oxygen (CMRO<sub>2</sub>) were calculated in the contrast-enhancing tumor (CET) and peritumoral non-enhancing T2 hyperintense region (NET2), using an artificial neural network. We demonstrated that OEF in CET was significantly lower (<i>p</i> = 0.03) for glioblastomas than metastases, all features were significantly higher (<i>p</i> = 0.01) in CET than in NET2 for metastasis patients only, and the ratios of CET/NET2 for CBF (<i>p</i> = 0.04) and CMRO<sub>2</sub> (<i>p</i> = 0.01) were significantly higher in metastasis patients than in glioblastoma patients. Discriminative power of a support-vector machine classifier was highest with a combination of two features, yielding an area under the receiver operating characteristic curve of 0.94 with 93% diagnostic accuracy. QSM + qBOLD allows for robust differentiation of glioblastoma and cerebral metastasis while yielding insights into tumor oxygenation.Hakim BaazaouiSimon HubertusMáté E. MarosSherif A. MohamedAlex FörsterLothar R. SchadHolger WenzMDPI AGarticlebrain metastasisglioblastomamachine learningoxygenationtumor infiltrationTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9928, p 9928 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	brain metastasis glioblastoma machine learning oxygenation tumor infiltration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	brain metastasis glioblastoma machine learning oxygenation tumor infiltration Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hakim Baazaoui Simon Hubertus Máté E. Maros Sherif A. Mohamed Alex Förster Lothar R. Schad Holger Wenz Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
description	Glioblastoma may appear similar to cerebral metastasis on conventional MRI in some cases, but their therapies differ significantly. This prospective feasibility study was aimed at differentiating them by applying the quantitative susceptibility mapping and quantitative blood-oxygen-level-dependent (QSM + qBOLD) model to these entities for the first time. We prospectively included 15 untreated patients with glioblastoma (n = 7, median age: 68 years, range: 54–84 years) or brain metastasis (n = 8, median age 66 years, range: 50–78 years) who underwent preoperative MRI including multi-gradient echo and arterial spin labeling sequences. Oxygen extraction fraction (OEF), cerebral blood flow (CBF) and cerebral metabolic rate of oxygen (CMRO<sub>2</sub>) were calculated in the contrast-enhancing tumor (CET) and peritumoral non-enhancing T2 hyperintense region (NET2), using an artificial neural network. We demonstrated that OEF in CET was significantly lower (<i>p</i> = 0.03) for glioblastomas than metastases, all features were significantly higher (<i>p</i> = 0.01) in CET than in NET2 for metastasis patients only, and the ratios of CET/NET2 for CBF (<i>p</i> = 0.04) and CMRO<sub>2</sub> (<i>p</i> = 0.01) were significantly higher in metastasis patients than in glioblastoma patients. Discriminative power of a support-vector machine classifier was highest with a combination of two features, yielding an area under the receiver operating characteristic curve of 0.94 with 93% diagnostic accuracy. QSM + qBOLD allows for robust differentiation of glioblastoma and cerebral metastasis while yielding insights into tumor oxygenation.
format	article
author	Hakim Baazaoui Simon Hubertus Máté E. Maros Sherif A. Mohamed Alex Förster Lothar R. Schad Holger Wenz
author_facet	Hakim Baazaoui Simon Hubertus Máté E. Maros Sherif A. Mohamed Alex Förster Lothar R. Schad Holger Wenz
author_sort	Hakim Baazaoui
title	Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
title_short	Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
title_full	Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
title_fullStr	Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
title_full_unstemmed	Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study
title_sort	artificial neural network-derived cerebral metabolic rate of oxygen for differentiating glioblastoma and brain metastasis in mri: a feasibility study
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4b5856c301b04c5784719615773daec1
work_keys_str_mv	AT hakimbaazaoui artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT simonhubertus artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT mateemaros artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT sherifamohamed artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT alexforster artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT lotharrschad artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy AT holgerwenz artificialneuralnetworkderivedcerebralmetabolicrateofoxygenfordifferentiatingglioblastomaandbrainmetastasisinmriafeasibilitystudy
_version_	1718437598496555008

Artificial Neural Network-Derived Cerebral Metabolic Rate of Oxygen for Differentiating Glioblastoma and Brain Metastasis in MRI: A Feasibility Study

Ejemplares similares