Brain tumour extraction from MRI images using bounding-box with level set method

Abstract

Brain tumour segmentation is a critical step in surgical planning and treatment planning. A substantial medical informatics assignment is to perform indexing of patient databases according to size, location, and other characteristics of brain tumours based on magnetic resonance (MR) imagery. This requires segmenting tumours within images from different MR modalities. Automatic brain tumour extraction from MR modalities remains a challenging, computationally demanding assignment. Image segmentation performs an essential role in image processing. The goal of image segmentation is to group the pixels into salient image regions i.e. regions corresponding to individual surfaces, objects, or natural parts of objects. This paper deals with the implementation of Simple Algorithm for locating and segmenting tumour in brain MR images. Tumour is an abnormally increasing growth of tissues in any part of the body. They are of different types and hold different characteristics and treatment. This paper uses computer aided method for segmentation (detection) of brain tumour based on the combination of two algorithms. This method allows the segmentation of tumour tissue with precision and consistency in comparison with manual segmentation. Also, it also reduces the time for analysis. At the end, the tumour is extracted from the MR image and its exact position and the shape is also determined.