An Iterative Implementation of Level Set for Precise Segmentation of Brain Tissues and Abnormality Detection from MR Images

In this paper, an iterative implement of level set methodology has been proposed for the precise segmentation of normal and abnormal tissues in magnetic resonance imaging (MRI) brain images. In this segmentation, the normal tissues such as WM (white matter), GM (grey matter), and CSF (cerebrospinal fluid) with other regions of human head such as skull, marrow, and muscles skin are segmented and abnormal tissues such as haemorrhage, oedema, and tumour can be segmented if any. The segmentation is done by using iterative three region level set method based on the condition sharp peak greater than three. The iterative segmented component generates a hierarchical structure for correct segmentation. The performance of the segmentation method is estimated by different metrics such as accuracy, similarity index, and relative error. The performance of segmentation method is examined using a defined set of MRI brain.