Andy Devos

Brain tumor classification based on long echo proton MRS signals

There has been a growing research interest in brain tumor classification based on proton magnetic resonance spectroscopy (1H MRS) signals. Four research centers within the EU funded INTERPRET project have acquired a significant number of long echo 1H MRS signals for brain tumor classification. In this paper, we present an objective comparison of several classification techniques applied to the discrimination of four types of brain tumors: meningiomas, glioblastomas, astrocytomas grade II and metastases. Linear and non-linear classifiers are compared: linear discriminant analysis (LDA), support vector machines (SVM) and least squares SVM (LS-SVM) with a linear kernel as linear techniques and LS-SVM with a radial basis function (RBF) kernel as a non-linear technique. Kernel-based methods can perform well in processing high dimensional data. This motivates the inclusion of SVM and LS-SVM in this study. The analysis includes optimal input variable selection, (hyper-) parameter estimation, followed by performance evaluation. The classification performance is evaluated over 200 stratified random samplings of the dataset into training and test sets. Receiver operating characteristic (ROC) curve analysis measures the performance of binary classification, while for multiclass classification, we consider the accuracy as performance measure. Based on the complete magnitude spectra, automated binary classifiers are able to reach an area under the ROC curve (AUC) of more than 0.9 except for the hard case glioblastomas versus metastases. Although, based on the available long echo 1H MRS data, we did not find any statistically significant difference between the performances of LDA and the kernel-based methods, the latter have the strength that no dimensionality reduction is required to obtain such a high performance.

Bagging Linear Sparse Bayesian Learning Models for Variable Selection in Cancer Diagnosis

This paper investigates variable selection (VS) and classification for biomedical datasets with a small sample size and a very high input dimension. The sequential sparse Bayesian learning methods with linear bases are used as the basic VS algorithm. Selected variables are fed to the kernel-based probabilistic classifiers: Bayesian least squares support vector machines (BayLS-SVMs) and relevance vector machines (RVMs). We employ the bagging techniques for both VS and model building in order to improve the reliability of the selected variables and the predictive performance. This modeling strategy is applied to real-life medical classification problems, including two binary cancer diagnosis problems based on microarray data and a brain tumor multiclass classification problem using spectra acquired via magnetic resonance spectroscopy. The work is experimentally compared to other VS methods. It is shown that the use of bagging can improve the reliability and stability of both VS and model prediction

Does the combination of magnetic resonance imaging and spectroscopic imaging improve the classification of brain tumours

Magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI) play an important role in the noninvasive diagnosis of brain tumours. We investigate the use of both MRI and MRSI, separately and in combination with each other for classification of brain tissue types. Many clinically relevant classification problems are considered; for example healthy versus tumour tissues, low- versus high-grade tumours. Linear as well as nonlinear techniques are compared. The classification performance is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). In general, all techniques achieve a high performance, except when using MRI alone. For example, for low- versus high-grade tumours, low- versus high-grade gliomas, gliomas versus meningiomas, respectively a test AUC higher than 0.91, 0.93 and 0.98 is reached, when both MRI and MRSI data are used.

Classification of Brain Tumours by Pattern Recognition of Magnetic Resonance Imaging and Spectroscopic Data

Abstract The medical diagnosis of brain tumours is one of the main applications of Magnetic Resonance (MR). Magnetic Resonance consists of two main branches: Imaging and Spectroscopy. Magnetic Resonance Imaging is the radiologic technique applied to produce high-quality images for diagnostic purposes. Magnetic Resonance Spectroscopy provides chemical information about metabolites present in the brain, such as their concentrations. Both Imaging and Spectroscopy can be exploited for the grading and typing of brain tumours, also called classification. The present gold standard to diagnose an abnormal brain mass is the histopathological analysis of a biopsy. However, a biopsy is riskful for the patient and therefore it would be very benificial if a diagnostic tool based on non-invasive techniques such as MR would be used to aid or even avoid the current gold standard. Classification of brain tumours is very interdisciplinairy and involves many aspects of medicine, engineering and mathematics. The development of a medical decision support tool covers data collection, specific pre-processing, exploitation of the useful features for classification and testing of the classification. The domain-specific knowledge of neurologists and radiologists is invaluable to guarantee a diagnostic tool applicable in daily clinical practice. This chapter provides an overview of the NMR methodology and its applications to brain tumour diagnosis. Spectral pre-processing issues such as normalization and baseline correction, which could have an influence on the accuracy of the classification, are discussed. A wealth of methods exists for feature extraction and classification of MR data; principal component analysis and mixture modelling are covered as unsupervised techniques and linear discriminant analysis and support vector machines as supervised ones. The described methods were tested on MRI and MRS data of healthy as well as brain tumour tissue, acquired in the framework of the EU-funded INTERPRET project. Results of the INTERPRET project illustrate that imaging and spectroscopic data are complementary for the accurate diagnosis of brain tumour tissue. The chapter arguments for a strong focus on the fusion of MR imaging and spectroscopic data and non-MR data, in the framework of further development and improvement of a medical decision support tool.