Title :
A validation framework for MR image segmentation
Author :
Zheng, Xia ; Dai, Mo ; Zhou, Mingquan
Author_Institution :
State Key Lab. of Cognitive Neurosci. & Learning, Beijing Normal Univ., Beijing
Abstract :
A validation framework for MR image segmentation is proposed in this paper. It includes three stages: intensity inhomogeneity (IIH) correction, noise suppression without blurring structures and tissue classification. Based on MR brain images, in the first stage, an improved process is used to implement IIH correction. Subsequently, a new enhancement method on moments for noise removal and edge sharpening is introduced in the second stage. It owes much to properties of Gauss-Hermite moments (GHMs). In the third stage, FCM is used to classify two different tissues: white matter (WM) and gray matter (GM). For cerebrospinal fluid (CSF), it comes from subtraction result between T1 and T2 weighted images. Examples on simulated images have been reported to show the efficiency of this framework.
Keywords :
Gaussian noise; biological tissues; biomedical MRI; brain; edge detection; fuzzy set theory; image denoising; image enhancement; image segmentation; medical image processing; pattern classification; Gauss-Hermite moment; MR brain image segmentation; cerebrospinal fluid; edge sharpening; fuzzy c-means algorithm; gray matter; image enhancement; intensity inhomogeneity correction; noise removal; noise suppression; validation framework; white matter; Brain; Gaussian processes; Image edge detection; Image segmentation; Magnetic resonance imaging; Noise reduction; Pattern analysis; Pattern recognition; Signal to noise ratio; Wavelet analysis; Gauss-Hermite moments; Intensity Inhomogeneity Correction; MRI; Segmentation;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-2238-8
Electronic_ISBN :
978-1-4244-2239-5
DOI :
10.1109/ICWAPR.2008.4635759
