Brain White Matter Hyperintensities Segmentation of T2-FLAIR MRI Using L*a*b* Color Transformation and K-Neasrest Neighbor Means Classifier

White matter hyperintensities(WMH) on T2-FLAIR Magnetic Resonance Imaging(MRI) has the association with risk of stroke or dementia such as Alzheimer’s diseases and vascular dementia. In many researches, WMH are also demonstrated that they can predict an increased risk of cerebrovascular diseases. WMH are counted as an intermediate quantitative marker to identify a new risk factor. In this paper, we propose a method to extract WMH areas from T2- FLAIR MRI. The proposed method consists of two segmentation steps. In the first phase, a combined method of k-means clustering with morphology techniques is applied to separate brain matter from cranium on MRI input image. Then in the second phase, the grayscale brain matter is transformed to L*a*b* color space to extend the difference from pixel to pixel and k-nearest neighbor means classifier algorithm is used to separate brain image into 3 different classes of WMH area, non-WMH area and background area. The experiments on real T2- FLAIR MRI demonstrated that our proposed approach results to good performances with high values in Recall and Precision measurements, outperforms the Graph Cut in segment minor WMH and performance across all datasets is more stable.