Predicting primary outcomes of brain tumor patients with advanced neuroimaging MRI measures

Article ID	Journal	Published Year	Pages	File Type
8684898	Interdisciplinary Neurosurgery	2018	40 Pages	PDF

Abstract

This study showed that advanced neuroimaging data with machine learning methods can potentially predict patient outcomes and reveal influential factors driving the predictions.

Keywords

ICA FSPGR ROI RFE rCBV NEX DWI MNI EPI GBM MMSE LOOCV DTI FWHM QOL Quality of life Advanced Normalization Tools Attention-Deficit/Hyperactivity Disorder Mini-mental state exam ADHD verbal fluency Independent component analysis Leave-one-out cross-validation Controlled Oral Word Association Test Diffusion weighted imaging Echo-planar imaging diffusion tensor imaging fMRI functional magnetic resonance imaging number of excitations Relative cerebral blood volume Recursive feature elimination SMA echo time Repetition time inversion time full-width at half-maximum Machine-learning LAD SVM Support vector machine mean diffusivity supplementary motor area region of interest Ants Montreal Neurological Institute fractional anisotropy Outcome prediction COWAT Glioblastoma multiforme

Related Topics

Health Sciences Medicine and Dentistry Clinical Neurology

Predicting primary outcomes of brain tumor patients with advanced neuroimaging MRI measures

Authors

Svyat Vergun, Josh I. Suhonen, Veena A. Nair, J.S. Kuo, M.K. Baskaya, Camille Garcia-Ramos, Elizabeth E. Meyerand, Vivek Prabhakaran,