Automated segmentation of white matter lesions using global neighbourhood given contrast feature-based random forest and markov random field
Recent studies show that, cerebral White MatterLesion (WML) is related to cerebrovascular diseases,cardiovascular diseases, dementia and psychiatric disorders.Manual segmentation of WML is not appropriate for long termlongitudinal studies because it is time consuming and it showshigh intra- and inter-rater variability. In this paper, a fullyautomated segmentation method is utilized to segment WMLfrom brain Magnetic Resonance Imaging (MRI). The segmentationmethod uses a combination of global neighbourhoodgiven contrast feature-based Random Forest (RF) classifier andMarkov Random Field (MRF) to segment WML. To removefalse positive lesions we use a rule based morphological postprocessingoperation. Quantitative evaluation of the proposedmethod was performed on 24 subjects of ENVIS-ion study.The segmentation results were validated against the manualsegmentation, performed by an experienced radiologist andwere compared to a recenlty published WML segmentationmethod. The results show a dice similarity index of 0.75 forhigh lesion load, 0.71 for medium lesion load and 0.60 for lowlesion load.
