Method of multi-region tumour segmentation in brain MRI images using grid-based segmentation and weighted bee swarm optimisation

Multi-region segmentation plays a major role in numerous medical diagnostics especially brain tumour identification and classification in Magnetic Resonance Imaging (MRI). Brain tumour segmentation is used in medical field for early diagnostics and detection of tumour. The main goal of this work is to improve the performance of detection by using grid based techniques with Weighted Bee Swarm Intelligence and K-means clustering. This technique is more effective due to hybrid combination of segmentation and optimisation as it seems to possess specific tasks of image information and detection to obtain a detailed and accurate image analysis. Grid based segmentation balance overall computation time and reduces complexity. Weighted Bee Swarm Optimisation is used to optimise segmentation parameters to get maximum performance. The various informative regions such as cerebrospinal fluid, grey matter, white matter are segmented by using proposed algorithm which will be most useful to study and characterise the tumour. The experimental outcomes show that the proposed strategy enhances performance measures in terms of sensitivity and specificity analysis. The performance of this technique is also improved by a factor of 1.5%.