Author:

Keywords:

SISTA, PSI_MIC, Science & Technology, Life Sciences & Biomedicine, Technology, Biophysics, Radiology, Nuclear Medicine & Medical Imaging, Spectroscopy, brain tumor, nosologic image, magnetic resonance imaging (MRI), magnetic resonance spectroscopic imaging (MRSI), classification, segmentation, class probabilities, KERNEL LOGISTIC-REGRESSION, TUMOR SEGMENTATION, SPECTROSCOPY, IMAGES, GLIOMAS, MODEL, QUANTIFICATION, FRAMEWORK, SYSTEM, Adult, Brain, Brain Neoplasms, Female, Glioma, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Male, Middle Aged, 0304 Medicinal and Biomolecular Chemistry, 0903 Biomedical Engineering, 1103 Clinical Sciences, Nuclear Medicine & Medical Imaging, 3202 Clinical sciences, 4003 Biomedical engineering

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.