Title :
Segmentation of large brain lesions
Author :
Hojjatoleslami, S.A. ; Kruggel, F.
Author_Institution :
Max-Planck-Inst. of Cognitive Neuro-Sci., Leipzig, Germany
fDate :
7/1/2001 12:00:00 AM
Abstract :
This paper describes a region-growing algorithm for the segmentation of large lesions in T 1-weighted magnetic resonance (MR) images of the head. The algorithm involves a gray level similarity criterion to expand the region and a size criterion to prevent from over-growing outside the lesion. The performance of tile algorithm is evaluated and validated on a series of pathologic three-dimensional MR images of the head.
Keywords :
biomedical MRI; brain; image segmentation; medical image processing; T/sub 1/-weighted magnetic resonance images; brain MRI; gray level similarity criterion; head; magnetic resonance imaging; medical diagnostic imaging; pathologic three-dimensional MR images series; region expansion; region-growing algorithm; size criterion; Hemorrhaging; Image segmentation; Inspection; Lesions; Magnetic heads; Magnetic resonance; Magnetic resonance imaging; Multiple sclerosis; Neuroscience; Protocols; Algorithms; Brain; Brain Diseases; Fourier Analysis; Image Processing, Computer-Assisted; Imaging, Three-Dimensional; Magnetic Resonance Imaging; Sensitivity and Specificity;
Journal_Title :
Medical Imaging, IEEE Transactions on
