Title :
MRI Brain Extraction with Combined Expectation Maximization and Geodesic Active Contours
Author :
Huang, Albert ; Abugharbieh, Rafeef ; Tam, Roger ; Traboulsee, Anthony
Author_Institution :
Dept. of Elec. & Comp. Eng., British Columbia Univ., Vancouver, BC
Abstract :
This paper presents a new fully automated method for the extraction of brain cortex from Tl-weighted magnetic resonance imaging (MRI) head scans. Combined with the expectation maximization (EM) algorithm, and a hybrid of pre- and post-processing techniques, incorporating mathematical morphology and connected component analysis, geodesic active contours are evolved in 3D space to segment the cortex. The robustness and accuracy of our proposed method are validated with both synthetic and real MRI data. Our method outperforms standard techniques including the brain extraction tool (BET) and statistical parametric mapping (SPM) by lowering the misclassification rate, especially when analyzing real MRI data
Keywords :
biomedical MRI; brain; differential geometry; expectation-maximisation algorithm; image classification; image segmentation; mathematical morphology; MRI brain extraction; Tl-weighted magnetic resonance imaging head scans; brain cortex; brain extraction tool; connected component analysis; cortex segmentation; expectation maximization algorithm; geodesic active contours; mathematical morphology; misclassification rate; statistical parametric mapping; Active contours; Algorithm design and analysis; Data mining; Image segmentation; Magnetic analysis; Magnetic heads; Magnetic resonance imaging; Morphology; Robustness; Scanning probe microscopy; biomedical image processing; brain extraction; magnetic resonance imaging (MRI);
Conference_Titel :
Signal Processing and Information Technology, 2006 IEEE International Symposium on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9753-3
Electronic_ISBN :
0-7803-9754-1
DOI :
10.1109/ISSPIT.2006.270779