1. Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging
- Author
-
Benjamin M. Ellingson, Ali Nabavizadeh, Stephen J Bagley, Donald M. O'Rourke, Elizabeth Mamourian, Jeffrey B. Ware, Hannah Anderson, Catalina Raymond, Samantha Guiry, Christos Davatzikos, Anahita Fathi Kazerooni, Hamed Akbari, Steven Brem, Chiharu Sako, Jingwen Yao, and Arati Desai
- Subjects
Male ,Data Interpretation ,Image Processing ,030218 nuclear medicine & medical imaging ,Mice ,0302 clinical medicine ,Nuclear magnetic resonance ,Computer-Assisted ,Image Processing, Computer-Assisted ,Tumor Microenvironment ,Contrast (vision) ,media_common ,Cancer ,Principal Component Analysis ,Multidisciplinary ,Chemistry ,Statistical ,Hydrogen-Ion Concentration ,Middle Aged ,Magnetic Resonance Imaging ,Regression ,Data Interpretation, Statistical ,Principal component analysis ,Biomedical Imaging ,Medicine ,Female ,Dynamic susceptibility ,media_common.quotation_subject ,Science ,Article ,03 medical and health sciences ,Rare Diseases ,Clinical Research ,medicine ,Animals ,Humans ,Magnetization transfer ,Aged ,Neoplasm Staging ,Tumor microenvironment ,Animal ,Neurosciences ,medicine.disease ,Hyperintensity ,Brain Disorders ,Brain Cancer ,CNS cancer ,Disease Models, Animal ,Disease Models ,Cancer imaging ,Neoplasm Grading ,Glioblastoma ,030217 neurology & neurosurgery - 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
- Published
- 2021