Magnetic Resonance Signal Processing in Medical Applications

0386210 - ÚPT 2013 RIV RE eng C - Konferenční příspěvek (zahraniční konf.)
Mikulka, J. - Gescheidtová, E. - Bartušek, Karel
Magnetic Resonance Signal Processing in Medical Applications.
ICONS 2012: The Seventh Interatnional Conference on Systems. Saint Gilles: IARIA, 2012, s. 148-153. ISBN 978-1-61208-184-7.
[GlobeNet 2012: ICN 2012, ICONS 2012, VisGra 2012, DBKDA 2012. Saint Gilles (RE), 29.02.2012-05.03.2012]
Grant CEP: GA MŠMT ED0017/01/01; GA ČR GAP102/11/0318
Institucionální podpora: RVO:68081731
Klíčová slova: magnetic resonance * biomedical image processing * image segmentation * level set * active countour * edge analysis * noise suppression * volumetry
Kód oboru RIV: JA - Elektronika a optoelektronika, elektrotechnika

Image processing in biomedical applications is an important developing issue. Many methods and approaches for image preprocessing, segmentation and visualization were described. It is necessary to choose a suitable segmentation method to create a correct three-dimensional model. The accuracy of reconstruction depends on precision of regions boundary determining in magnetic resonance slices. A frequent application is detection of soft tissues. To obtain images of the soft tissues mentioned, tomography based on magnetic resonance is usually used. Ideally, several tissue slices in three orthogonal planes (sagittal, coronal, transverse) are acquired. Following reconstruction of shape of examined tissues is the most accurate. In case of acquired slices only in one plane, the high spatial information lost occurs by image acquisition. Then it is necessary to reconstruct the shape of tissue appropriately. At first the images are segmented and with use of particular segments the three dimensional model is composed. This article compares several segmentation approaches of magnetic resonance images and their results. The results of segmentation by active contour, thresholding, edge analysis by Sobel mask, watershed and region-based level set segmentation methods are compared. The results for different values of parameters of segmentation methods are compared. As the test image, slice of human liver tumour was chosen.
Trvalý link: http://hdl.handle.net/11104/0215499