A Unified Framework for Brain Segmentation in MR Images

Abstract

Brain MRI segmentation is an important issue for discovering the brain structure and diagnosis of subtle anatomical changes in different brain diseases. However, due to several artifacts brain tissue segmentation remains a challenging task. The aim of this paper is to improve the automatic segmentation of brain into gray matter, white matter, and cerebrospinal fluid in magnetic resonance images (MRI). We proposed an automatic hybrid image segmentation method that integrates the modified statistical expectation-maximization (EM) method and the spatial information combined with support vector machine (SVM). The combined method has more accurate results than what can be achieved with its individual techniques that is demonstrated through experiments on both real data and simulated images. Experiments are carried out on both synthetic and real MRI. The results of proposed technique are evaluated against manual segmentation results and other methods based on real T1-weighted scans from Internet Brain Segmentation Repository (IBSR) and simulated images from BrainWeb. The Kappa index is calculated to assess the performance of the proposed framework relative to the ground truth and expert segmentations. The results demonstrate that the proposed combined method has satisfactory results on both simulated MRI and real brain datasets.

Image Segmentation Methods and Applications in MRI Brain Images

“…Fuzzy algorithms also are sensitive to the initialization with regard to both speed and stability, but they are less sensitive to the initialization compared with other techniques [28,29].…”

Automatic Region-Based Brain Classification of MRI-T1 Data

“…For example the EM algorithm was proposed by Wells et al that iterates between the estimation of tissue class probability [ 7 , 8 ]. The main shortcoming of EM based techniques is that they are based on symmetric Gaussian distribution model for the intensity distribution of brain images that is not true in the real MRI [ 9 ]. The experimental results demonstrate that the distributions of tissue intensity do not exactly demonstrate a normal Gaussian distribution, particularly for noisy images [ 10 ].…”

“…The experimental results demonstrate that the distributions of tissue intensity do not exactly demonstrate a normal Gaussian distribution, particularly for noisy images [ 10 ]. Usually in real MR Images, the intensity distributions of brain tissues can vary asymmetrically in these images [ 4 , 9 , 11 ]. Consequently the intensity of individual tissues may display skewed or spread shapes between brain images that may not be well fitted by a Gaussian shape [ 4 , 11 , 12 ].…”

“…Consequently the intensity of individual tissues may display skewed or spread shapes between brain images that may not be well fitted by a Gaussian shape [ 4 , 11 , 12 ]. For example the CSF intensity on T1 brain images usually spread across a wide range at the lower end of the histogram and display an overlap with the GM tissue [ 4 , 9 , 11 ].…”

A Hybrid Method for Image Segmentation Based on Artificial Fish Swarm Algorithm and Fuzzyc-Means Clustering

“…As early as 1996, Chun and Yang have introduced intelligent algorithm into image segmentation field by researching the combination of genetic algorithm and FCM [ 7 ]. The hybrid algorithms [ 8 – 12 ] have more excellent performance to overcome the shortcomings of FCM.…”