Contemporary Technique for Detection of Brain Tumor in Fluid-Attenuated Inversion Recovery Magnetic Resonance Imaging (MRI) Images

Abstract

The MRI image segmentation and early detection of brain tumor are crucial pace for better planning of treatment and consequently improving patient survival. The manually assessment of acquired MRI images in the routine clinical process is difficult and time-consuming process, and as a result, the viable automatic segmentation mechanism is essential for evaluation of MRI images. The finding of feasible automatic segmentation framework for brain fluid-attenuated inversion recovery MRI image is not attentive in literature review. The research work implements a novel mechanism for classification and segmentation of brain MRI images. The framework consists of an automatic probabilistic expectation maximization Gaussian mixture model (EMGMM) to improve the segmentation process and improve the segmentation accuracy. In the proposed framework, MRI images classification and segmentation of tumor are obtained with superior accuracy. The contemporary framework is quantitatively evaluated on BraTS benchmark brain MRI image dataset.