Title :
Segmentation of MR brain images with bias artifact
Author :
Ardizzone, Edoardo ; Pirrone, Roberto ; Gambino, Orazio ; Alagn, Francesco
Author_Institution :
Comput. Sci. Dept., Univ. of Palermo, Palermo, Italy
Abstract :
Brain MR Images corrupted by RF-Inhomogeneity (bias artifact) exhibit brightness variations across the image. As a consequence, a standard fuzzy C-means (fcm) segmentation algorithm may fail. In this work we show a new general-purpose bias removing algorithm, which can be used as a pre-processing step for a fcm segmentation. We also compare our experimental results with the ones achieved by using E2D-HUM filter, showing an improvement in brain segmentation and bias removal.
Keywords :
biomedical MRI; brain; fuzzy set theory; image denoising; image segmentation; medical image processing; neurophysiology; MR Brain images; RF-inhomogeneity; bias artifact; bias removing algorithm; brightness variations; fuzzy C-means segmentation algorithm; image segmentation; preprocessing step; Brain; Brightness; Clustering algorithms; Cutoff frequency; Filtering; Image edge detection; Image segmentation; Information technology; Low pass filters; Phase estimation; MRI; RF-Inhomogeneity; bias; halo; segmentation;
Conference_Titel :
Information Technology and Applications in Biomedicine, 2009. ITAB 2009. 9th International Conference on
Conference_Location :
Larnaca
Print_ISBN :
978-1-4244-5379-5
Electronic_ISBN :
978-1-4244-5379-5
DOI :
10.1109/ITAB.2009.5394449
