Malignancy probability map as a novel imaging biomarker to predict malignancy distribution: employing MRS in GBM patients

Abstract

The main aim of this study was to propose a new statistical method for evaluation of spatial malignancy distribution within Magnetic Resonance Spectroscopy (MRS) grid in Glioblastoma Multiforme patients. Voxels with different malignancy probabilities were presented as a novel MRS-based Malignancy Probability Map (MPM). For this purpose, a predictive probability-based clustering approach was developed, including the two following steps: (1) Gaussian Mixture Model, (2) Quadratic Discriminate Analysis coupled with Genetic Algorithm. Clustered probability values from two methods were then integrated to exploit the MPM. Results show that the suggested method is able to estimate the malignancy distribution with over 90% sensitivity and specificity. The proposed MRS-based MPM has an acceptable accuracy for providing useful complementary information about regional diffuse glioma malignancy, with the potential to lead to better detection of tumoral regions with high probability of malignancy. So, it also may encourage the use of additional information of this map as a tool for dose painting.

Cancer metabolism in a snapshot: MRS(I)

“…The problem of imbalanced classes has also been tackled with the use of AdaBoost . Supervised pattern recognition techniques such as support vector machines, linear discriminant analysis or several different algorithms, and classifier fusion, are also used in the latest literature, mainly for diagnostic questions. These methodologies are, generally too sophisticated to be put in practice by purely clinical groups, and when methodologies are tested the norm is availability of very small datasets, although there are exceptions such as Reference 113 or 109.…”