Abstract
Purpose: The purpose of this paper is discriminating between tumor progression and response to treatment based on follow-up multi-parametric magnetic resonance imaging (MRI) data retrieved from glioblastoma multiforme (GBM) patients.Materials and Methods: Multi-parametric MRI data consisting of conventional MRI (cMRI) and advanced MRI [i.e., perfusion weighted MRI (PWI) and diffusion kurtosis MRI (DKI)] were acquired from 29 GBM patients treated with adjuvant therapy after surgery. We propose an automatic pipeline for processing advanced MRI data and extracting intensity-based histogram features and 3-D texture features using manually and semi-manually delineated regions of interest (ROIs). Classifiers are trained using a leave-one-patient-out cross validation scheme on complete MRI data. Balanced accuracy rate (BAR)–values are computed and compared between different ROIs, MR modalities, and classifiers, using non-parametric multiple comparison tests.Results: Maximum BAR–values using manual delineations are 0.956, 0.85, 0.879, and 0.932, for cMRI, PWI, DKI, and all three MRI modalities combined, respectively. Maximum BAR–values using semi-manual delineations are 0.932, 0.894, 0.885, and 0.947, for cMRI, PWI, DKI, and all three MR modalities combined, respectively. After statistical testing using Kruskal-Wallis and post-hoc Dunn-Šidák analysis we conclude that training a RUSBoost classifier on features extracted using semi-manual delineations on cMRI or on all MRI modalities combined performs best.Conclusions: We present two main conclusions: (1) using T1 post-contrast (T1pc) features extracted from manual total delineations, AdaBoost achieves the highest BAR–value, 0.956; (2) using T1pc-average, T1pc-90th percentile, and Cerebral Blood Volume (CBV) 90th percentile extracted from semi-manually delineated contrast enhancing ROIs, SVM-rbf, and RUSBoost achieve BAR–values of 0.947 and 0.932, respectively. Our findings show that AdaBoost, SVM-rbf, and RUSBoost trained on T1pc and CBV features can differentiate progressive from responsive GBM patients with very high accuracy.
Highlights
Glioblastoma multiforme (GBM) is the most common and malignant intracranial tumor (Burger et al, 1985), representing as much as 30% of primary brain tumors with increasing incidence in some geographic regions (Dobes et al, 2011)
Four MR modalities, two types of delineations, with a variable number of features from one to ten, summing up to a total of 560 balanced accuracy rate (BAR)–values. These BAR– values were grouped in several ways (e.g., 56 groups of 10 values), and a non-parametric comparison was made to account for statistical differences between groups
The maximum value is achieved using features extracted from Total tumor regions of interest (ROI) and not contrast enhancing region (CER)&non-enhancing region (NER) (0.956 vs. 0.947), we showed using non-parametric multiple comparison tests that it is recommended to use features from CER&NER, which could be defined by a simple threshold like the 90th percentile on T1 post-contrast (T1pc)-Total ROI
Summary
Glioblastoma multiforme (GBM) is the most common and malignant intracranial tumor (Burger et al, 1985), representing as much as 30% of primary brain tumors with increasing incidence in some geographic regions (Dobes et al, 2011). Magnetic resonance imaging (MRI) is the most widely used medical imaging technique for identifying the location and size of brain tumors. Conventional MRI (cMRI) has a limited specificity in determining the underlying type and grade of the brain tumor (Earnest et al, 1988; Dean et al, 1990). More advanced MR techniques like perfusion weighted MRI (PWI) and diffusion kurtosis MRI (DKI) are promising in the characterization of brain tumors as they give potentially more physiological information (Nelson and Cha, 2003; Rees, 2003; Vrabec et al, 2011). MD is a general parameter that accounts for the mean diffusivity in all directions, while MK might be a specific parameter for tissue structure (Jensen et al, 2005). Hypervascularity due to glioma-induced neoangiogenesis may show up as high relative cerebral blood volume (rCBV) while necrosis of different tissues may show up as low rCBV (Lund et al, 2005)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
