Computer Aided Detection of Brain Tumor in Magnetic Resonance Images

Abstract

Brain tumor is an abnormal mass of tissue with uncoordinated growth inside the skull which may invade and damage nerves and other healthy tissues. Non-homogeneities of the brain tissues result in inaccurate detection of tumor boundaries with the existing methods for contrast enhancement and segmentation of magnetic resonance images (MRI).This paper presents an improved framework for computer aided detection of brain tumor. This involves enhancement of cerebral MRI features by incorporating enhancement approaches of both the frequency and spatial domain. The proposed method requires de-noising in wavelet domain followed by enhancement using a non-linear enhancement function. Further an iterative enhancement algorithm is applied for enhancing the edges using the morphological filter. Segmentation of the brain tumor is finally obtained by employing large sized structuring elements along with thresholding. Simulation results along with the estimates of quality metrics portray significant improvement of contrast, enhancement of edges along with detection of boundaries in comparison to other recently developed methods. comprehensive survey indicates the exponential increase in the magnitude of research going on in the medical world for brain cancer indicating the fatal traits of brain tumor. An efficient image contrast enhancement module followed by edge enhancement and segmentation is the primary requirement of any computer aided detection system employed for medical diagnosis. In this paper, a new method for computer aided detection of brain tumor is proposed which consists of contrast improvement of cerebral MRI features followed by segmentation of targeted region of interest (ROI). The proposed framework will aid in the accurate diagnosis of tumor patients. This paper is structured as follows: section I gives a brief introduction of brain tumor. Existing image enhancement techniques have been discussed in the section-III, while an overview of wavelet transform has been given in the third section. Section-IV explains the proposed method. The objective evaluation parameters have been described in the fifth section and the experimental results discussed under section-VI. Seventh section draws the conclusion, whereas the scope for future improvement is given under section VIII.