Title :
Brain Tissue Segmentation Based On Corrected Gray-Scale Analysis
Author :
Wang, Jinghua ; Qiu, Maolin ; Papademetris, Xenophon ; Constable, R. Todd
Author_Institution :
The Anlyan Center, Yale Univ. Sch. of Med., New Haven, CT
Abstract :
Image signal-to-noise ratio (SNR) and signal intensity (SI) inhomogeneities are factors that strongly affect the accuracy and precision of brain tissue segmentations in magnetic resonance image (MRI). In this work, SNR and contrast of brain images are optimized by TR and inversion recovery time TI in multi-spectrum MRI data sets. SI inhomogeneities are measured in vivo using a recently developed method allowing improved correction. The three-Gaussian distribution model is used to fit histograms of the images to find the initialization parameters for an expectation-maximization (EM) segmentation algorithm. Compared with other methods, the field map method provides better correction of SI inhomogeneities and excellent segmentation results
Keywords :
Gaussian distribution; biological tissues; biomedical MRI; brain; expectation-maximisation algorithm; image segmentation; medical image processing; optimisation; brain tissue segmentation; corrected gray-scale analysis; expectation-maximization segmentation algorithm; field map method; image contrast; image signal-to-noise ratio; inversion recovery time; magnetic resonance image; multispectrum MRI; optimization; signal intensity inhomogeneities; three-Gaussian distribution model; Brain; Gray-scale; Histograms; Image segmentation; In vivo; Magnetic analysis; Magnetic field measurement; Magnetic resonance; Magnetic resonance imaging; Signal to noise ratio;
Conference_Titel :
Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the
Conference_Location :
Shanghai
Print_ISBN :
0-7803-8741-4
DOI :
10.1109/IEMBS.2005.1617112
