Certain investigations on MRI brain tumor segmentation using combined approaches

Abstract

Image segmentation is the process by which the original image is subdivided into its constituent regions or objects The level to which the subdivision is achieved depends on the problem being solved Simply the inputs of the image segmentation are images but the outputs are attributes extracted from images Image segmentation is an important initial task for higher level image processing such as object recognition or object tracking In medical image segmentation structures or objects of interest for segmentation include organs parts of pathology abnormalities such as brain tumors and brain tissues This research work proposed the methods to segment tumors on newlinebrain MRI images accurately by combining both region and boundary based segmentation methods The region based methods have drawbacks at the boundary of tumors and boundary based methods suffer from contour initialization problem In the combined approach the research work used the benefit of boundary based and region based method to overcome the problem of each other The region based method is used to initialize the boundary based method and the precise segmentation properties of the boundary based method used to overcome the problem of region based method at border of tumors newline