Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging
Abstract Glioblastoma (GBM) has high metabolic demands, which can lead to acidification of the tumor microenvironment. We hypothesize that a machine learning model built on temporal principal component analysis (PCA) of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI can be used to esti...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f3997d4247b045488e4da9cb506d56e2 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f3997d4247b045488e4da9cb506d56e2 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f3997d4247b045488e4da9cb506d56e22021-12-02T16:26:30ZQuantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging10.1038/s41598-021-94560-32045-2322https://doaj.org/article/f3997d4247b045488e4da9cb506d56e22021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94560-3https://doaj.org/toc/2045-2322Abstract Glioblastoma (GBM) has high metabolic demands, which can lead to acidification of the tumor microenvironment. We hypothesize that a machine learning model built on temporal principal component analysis (PCA) of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI can be used to estimate tumor acidity in GBM, as estimated by pH-sensitive amine chemical exchange saturation transfer echo-planar imaging (CEST-EPI). We analyzed 78 MRI scans in 32 treatment naïve and post-treatment GBM patients. All patients were imaged with DSC-MRI, and pH-weighting that was quantified from CEST-EPI estimation of the magnetization transfer ratio asymmetry (MTRasym) at 3 ppm. Enhancing tumor (ET), non-enhancing core (NC), and peritumoral T2 hyperintensity (namely, edema, ED) were used to extract principal components (PCs) and to build support vector machines regression (SVR) models to predict MTRasym values using PCs. Our predicted map correlated with MTRasym values with Spearman’s r equal to 0.66, 0.47, 0.67, 0.71, in NC, ET, ED, and overall, respectively (p < 0.006). The results of this study demonstrates that PCA analysis of DSC imaging data can provide information about tumor pH in GBM patients, with the strongest association within the peritumoral regions.Hamed AkbariAnahita Fathi KazerooniJeffrey B. WareElizabeth MamourianHannah AndersonSamantha GuiryChiharu SakoCatalina RaymondJingwen YaoSteven BremDonald M. O’RourkeArati S. DesaiStephen J. BagleyBenjamin M. EllingsonChristos DavatzikosAli NabavizadehNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Hamed Akbari Anahita Fathi Kazerooni Jeffrey B. Ware Elizabeth Mamourian Hannah Anderson Samantha Guiry Chiharu Sako Catalina Raymond Jingwen Yao Steven Brem Donald M. O’Rourke Arati S. Desai Stephen J. Bagley Benjamin M. Ellingson Christos Davatzikos Ali Nabavizadeh Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| description |
Abstract Glioblastoma (GBM) has high metabolic demands, which can lead to acidification of the tumor microenvironment. We hypothesize that a machine learning model built on temporal principal component analysis (PCA) of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI can be used to estimate tumor acidity in GBM, as estimated by pH-sensitive amine chemical exchange saturation transfer echo-planar imaging (CEST-EPI). We analyzed 78 MRI scans in 32 treatment naïve and post-treatment GBM patients. All patients were imaged with DSC-MRI, and pH-weighting that was quantified from CEST-EPI estimation of the magnetization transfer ratio asymmetry (MTRasym) at 3 ppm. Enhancing tumor (ET), non-enhancing core (NC), and peritumoral T2 hyperintensity (namely, edema, ED) were used to extract principal components (PCs) and to build support vector machines regression (SVR) models to predict MTRasym values using PCs. Our predicted map correlated with MTRasym values with Spearman’s r equal to 0.66, 0.47, 0.67, 0.71, in NC, ET, ED, and overall, respectively (p < 0.006). The results of this study demonstrates that PCA analysis of DSC imaging data can provide information about tumor pH in GBM patients, with the strongest association within the peritumoral regions. |
| format |
article |
| author |
Hamed Akbari Anahita Fathi Kazerooni Jeffrey B. Ware Elizabeth Mamourian Hannah Anderson Samantha Guiry Chiharu Sako Catalina Raymond Jingwen Yao Steven Brem Donald M. O’Rourke Arati S. Desai Stephen J. Bagley Benjamin M. Ellingson Christos Davatzikos Ali Nabavizadeh |
| author_facet |
Hamed Akbari Anahita Fathi Kazerooni Jeffrey B. Ware Elizabeth Mamourian Hannah Anderson Samantha Guiry Chiharu Sako Catalina Raymond Jingwen Yao Steven Brem Donald M. O’Rourke Arati S. Desai Stephen J. Bagley Benjamin M. Ellingson Christos Davatzikos Ali Nabavizadeh |
| author_sort |
Hamed Akbari |
| title |
Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| title_short |
Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| title_full |
Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| title_fullStr |
Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| title_full_unstemmed |
Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging |
| title_sort |
quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced mr imaging |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/f3997d4247b045488e4da9cb506d56e2 |
| work_keys_str_mv |
AT hamedakbari quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT anahitafathikazerooni quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT jeffreybware quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT elizabethmamourian quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT hannahanderson quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT samanthaguiry quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT chiharusako quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT catalinaraymond quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT jingwenyao quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT stevenbrem quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT donaldmorourke quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT aratisdesai quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT stephenjbagley quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT benjaminmellingson quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT christosdavatzikos quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging AT alinabavizadeh quantificationoftumormicroenvironmentacidityinglioblastomausingprincipalcomponentanalysisofdynamicsusceptibilitycontrastenhancedmrimaging |
| _version_ |
1718384090289274880 |