Intensity Standardization Simplifies Brain MR Image Segmentation

Abstract

Typically, brain MR images present significant intensity variation across patients and scanners. Consequently, training a classifier on a set of images and using it subsequently for brain segmentation may yield poor results. Adaptive iterative methods usually need to be employed to account for the variations of the particular scan. These methods are complicated, difficult to implement and often involve significant computational costs. In this paper, a simple, non-iterative method is proposed for brain MR image segmentation. Two preprocessing techniques, namely intensity inhomogeneity correction, and more importantly MR image intensity standardization, used prior to segmentation, play a vital role in making the MR image intensities have a tissue-specific numeric meaning, which leads us to a very simple brain tissue segmentation strategy.Vectorial scale-based fuzzy connectedness and certain morphological operations are utilized first to generate the brain intracranial mask. The fuzzy membership value of each voxel within the intracranial mask for each brain tissue is then estimated. Finally, a maximum likelihood criterion with spatial constraints taken into account is utilized in classifying all voxels in the intracranial mask into different brain tissue groups. A set of inhomogeneity corrected and intensity standardized images is utilized as a training data set. We introduce two methods to estimate fuzzy membership values. In the first method, called SMG (for simple membership based on a gaussian model), the fuzzy membership value is estimated by fitting a multivariate Gaussian model to the intensity distribution of each brain tissue whose mean intensity vector and covariance matrix are estimated and fixed from the training data sets. The second method, called SMH (for simple membership based on a histogram), estimates fuzzy membership value directly via the intensity distribution of each brain tissue obtained from the training data sets. We present several studies to evaluate the performance of these two methods based on 10 clinical MR images of normal subjects and 10 clinical MR images of Multiple Sclerosis (MS) patients. A quantitative comparison indicates that both methods have overall better accuracy than the k-nearest neighbors (kNN) method, and have much better efficiency than the Finite Mixture (FM) model based Expectation-Maximization (EM) method. Accuracy is similar for our methods and EM method for the normal subject data sets, but much better for our methods for the patient data sets.

Fig. 1

(a) A slice of a PD-weighted MRI scene with inhomogeneity. (b) The corresponding slice of the corrected scene.

Fig. 2

(a) Histograms of WM regions in 10 original PD-weighted MRI scenes. (b) A histogram obtained by combining the 10 histograms of (a) which represents WM intensity distribution in the PD scene. (c) Histograms of WM regions in the 10 corresponding standardized scenes. (d) Similar to (b) but obtained from the 10 histograms in (c).

Fig. 3

(a) One slice of an intensity inhomogeneity corrected and standardized PD-weighted MRI scene of the head of a normal human subject. (b) Corresponding T2-weighted slice. Segmentation result by using (c) kNN, (d) FM-EM, (e) SMG, (f) SMH. The tissues from dark to bright in (c), (d), (e), (f) are WM, GM, and CSF.

Fig. 4

(a) One slice of an intensity inhomogeneity corrected and standardized PD-weighted MRI scene of the head of a patient with Multiple Sclerosis. (b) Corresponding T2-weighted slice. Segmentation result by using (c) kNN, (d) FM-EM, (e) SMG, (f) SMH method. The tissues from dark to bright in (c), (d), (e), (f) are WM, GM, CSF, and MS lesions.

Fig. 5

(a) The result of kNN segmentation of the scene of Figure 3(a), (b) obtained by first performing only inhomogeneity correction but no standardization. (b) As in (a) but for the scene in Figure 4(a), (b).