White matter hyper-intensities automatic identification and segmentation in magnetic resonance images

A methodology for automatic identification and segmentation of white matter hyper-intensities appearing in magnetic resonance images of brain axial cuts is presented. To this end, a sequence of image processing technics is employed to form an image where the hyper-intensities in white matter differ notoriously from the rest of the objects. This pre-processing stage facilitates the posterior process of identification and segmentation of the hyper-intensity volumes. The proposed methodology was tested on 55 magnetic resonance images from six patients. These images were analysed by the proposed system and the resulted hyper-intensity images were compared with the images manually segmented by experts. The experimental results show the mean rate of true positives of 0.9, the mean rate of false positives of 0.7 and the similarity index of 0.7; it is worth commenting that the false positives are found mostly within the grey matter not causing problems in early diagnosis. The proposed methodology for magnetic resonance image processing and analysis may be useful in the early detection of white matter lesions. Nowadays, magnetic resonance imaging (MRI) is an important tool widely used in different medical applications. Among the different types of possibly disorders detected with MRI images are those of brain axial cuts used to detect various diseases character-ised by white matter abnormalities; their accurate detection is a challenging problem (Gordillo, Montseny, & Sobrevilla, 2013). White matter lesions are described as white matter hyper-intensities (WMH) that can be found within normal white matter tissue regions as brighter image objects when MRI uses T-2-weighted and fluid attenuated inversion recovery (FLAIR) (Raniga et al., 2011). The problem of WMH segmentation is difficult due to small differences in brightness between normal and injured regions that might vary in an entire image. Manual seg-mentation is possible, but is a time-consuming task and subject to operator variability; reproducing a manual segmentation result is difficult and the level of confidence ascribed suffers accordingly (Withey, Koles, software. NFSI-ICFBI, & heart, 2007). For these reasons , automatic WMH segmentation is preferable, but this task is rather difficult and it remains an active research area (Gordillo et al. Recently, a number of methods for WMH segmentation were proposed in literature. A comprehensive study of state-of-the-art MRI tumour segmentation techniques can be found in Gordillo et al. The most efficient, in our opinion, technique that does not refer to specific lesions and describe the automatic WMH segmentation using T-2 weighted FLAIR images …