No abstract

A new technique is presented to create nosologic images of the brain based on magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI). A nosologic image summarizes the presence of different tissues and lesions in a single image by color coding each voxel or pixel according to the histopathological class it is assigned to. The proposed technique applies advanced methods from image processing as well as pattern recognition to segment and classify brain tumors. First, a registered brain atlas and a subject-specific abnormal tissue prior, obtained from MRSI data, are used for the segmentation. Next, the detected abnormal tissue is classified based on supervised pattern recognition methods. Class probabilities are also calculated for the segmented abnormal region. Compared to previous approaches, the new framework is more flexible and able to better exploit spatial information leading to improved nosologic images. The combined scheme offers a new way to produce high-resolution nosologic images, representing tumor heterogeneity and class probabilities, which may help clinicians in decision making. INTRODUCTIONContrast-enhanced magnetic resonance imaging (MRI) is an important tool for the anatomical assessment of brain tumors. As a consequence, automatic brain tumor segmentation based on MRI is a widely studied topic (1-9). Nowadays, techniques based on thresholds, region growing, clustering, Markov random fields, classification algorithms, and artificial neural networks have been used and accurate segmentation results have been reported after comparison with manual tumor segmentation by an expert. However, several diagnostic questions, such as the type and grade of the tumor, are difficult to address using conventional MRI. The histopathological characterization of a tissue specimen remains the gold standard, despite the associated risks of surgery to obtain a biopsy. In recent years, the use of magnetic resonance spectroscopy (MRS), which provides metabolic information, is increasingly being used for more detailed and specific noninvasive evaluation of brain tumors. In particular magnetic resonance spectroscopic imaging (MRSI), which provides quantitative metabolite maps of the brain, is attractive as this may also enable to visualize the heterogeneous spatial extent of tumors, both inside and outside the MRI detectable lesion. However, the individual inspection and analysis of the many spectral patterns, obtained by MRSI, remains extremely timeconsuming and requires specific spectroscopic expertise. Therefore, it is not practical in a clinical setting, where automated processing and evaluation of the MRSI data as well as easy and rapid display of the results as images or maps are needed for routine clinical interpretation of an exam.As such, the term nosologic image was introduced for an image which indicates a specific tissue type in a certain color (10). Szabo de Edelenyi et al. used pattern recognition techniques and combined one specific contrast from MRI with spectroscopic informat...

Nowadays, MRSI represents a powerful non-invasive diagnostic tool. The ability of Magnetic Resonance Spectroscopy to detect metabolites is already very useful in daily radiologic practice since it provides significant biochemical information on the molecules of the organism under investigation. MRSI data can also be exploited in tissue segmentation techniques, which play a crucial role in many biomedical applications, such as the quantification of tissue volumes, localization of possible pathologies, improvement of pre-surgical diagnosis, and optimization of the surgical approach, therapy planning, etc. A variety of methods are available in the literature. They are often used in combination in order to solve different segmentation problems.They can be divided into several categories: thresholding techniques (1), region growing techniques (2), clustering techniques (3), Markov random field models (4), classifiers (5), artificial neural networks (6), etc. In this article, a fast and reliable tissue segmentation technique, based on a statistical method called Canonical Correlation Analysis (CCA), is proposed. This method is the multivariate variant of the ordinary correlation analysis and has already been successfully applied to functional Magnetic Resonance Imaging data in order to map sensor, motor, and cognitive functions to specific areas in the brain (7). Here CCA is adapted for MRSI data processing in order to detect possible homogeneous tissue regions, such as tumor regions, characterizing the considered sample. The goal is achieved by combining the spectral-spatial information provided by the MRSI data set and a signal subspace that models the spectrum of a characteristic tissue type, which may be present in the organ under investigation and, therefore, needs to be detected. More precisely, CCA quantifies the relationship between two sets of variables, magnitude spectra of the measured data and signal subspace, by means of correlation coefficients. These coefficients are afterward exploited in order to construct nosologic images (8) in which all the detected tissues are visualized. Such images can be easily interpreted by radiologists and physicians and, along with clinical and radiologic information, can improve the accuracy of the diagnosis.Extensive studies, performed on simulated as well as in vivo prostate MRSI data, were carried out in order to explore the properties of the proposed method. Moreover, the performance of CCA and ordinary correlation analysis was compared. The aforementioned studies show that CCA significantly outperforms ordinary correlation analysis in terms of accuracy and robustness.The article is organized as follows. In the Theory section, the basic definition of CCA is introduced and 3 possible implementations are outlined. In the Methods section, the application of CCA to MRSI data is described and the set up for the simulation studies and the acquisition environment of the in vivo studies is defined. In the Results and Discussion section, the results of the simulation and in viv...

No abstract