A DETAILED STUDY ON MRI BRAIN TUMOR DETECTION AND SEGMENTATION TECHNIQUES

Abstract In recent days, brain tumor is a serious cause for increasing humanity among people. During the past few decades, the number of people suffering and fading from brain tumors has been increased to 300 per year. Detecting and classifying the tumor in Magnetic Resonance Imaging (MRI) is a critical and challenging task in medical image processing. Because, the MRI provides the detailed information related to anatomical structures and potential abnormal tissues. So, the detection and segmentation of brain tumor plays an essential role in medical imaging and it helps to find the exact size and location of the tumor. For this purpose, different image processing techniques are proposed in the existing works. This paper reviews some of the existing research works related to brain tumor detection and segmentation. The stages involved in the brain tumor segmentation system are as follows: preprocessing, feature extraction, classification and segmentation. The preprocessing is an initial stage in any medical image processing applications. In this stage, the unwanted and irrelevant noise in the given image are eliminated. After that, the features of the filtered image are extracted to detect the edges. Hence, the classification technique is employed to determine whether the given image is normal or abnormal. If it is an abnormal image, the segmentation technique is applied to segment the exact portion of the tumor.