University of Nijmegen, The Netherlands - Department of Analytical Chemistry
In radiology, magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI) play an increasingly important role. However, the wealth of data available to the radiologist makes it more difficult to extract the relevant information. One way to summarise information from several congruent images is to show a segmented image, i.e. an image where pixels are clustered.
In this presentation, the use of model-based clustering for segmentation of MRI images of patients with brain tumours is discussed. A second type of data, where complete spectra are recorded at specific locations in the brain (MRSI data), is also used in model-based clustering. The results are in good agreement, and show the potential for clinical applications.