Automatic brain tumour detection and neovasculature assessment with multiseries MRI analysis
The paper deals with the segmentation of brain tumours in Magnetic Resonance (MR) images. The segmentation method developed is based on the analysis of three MR series namely: T1-weighted (T1W), contrast enhanced T1W (CE-T1W) and perfusion maps images. The differential images after and before contrast agent administration are segmented with the use of the Kernelised Fuzzy C-Means (KFCM) method, yielding a binary mask of the suspected tumour. Next, the mask is superimposed over the perfusion maps. The perfusion intensities of corresponding areas in both brain hemispheres are compared. The results obtained for ten subjects with glioblastoma multiforme (GBM) and anaplastic astrocytoma (AA) are discussed.