Detection and Classification of Tumors in Ct Images

Image segmentation is the process of partitioning a digital image into multiple segments or set of pixels. The objective of image segmentation is to group pixels into a prominent image region. In this paper, segmentation of Gray level images is used to provide information such as anatomical structure and identifying the Region of Interest i.e. locate tumor, lesion and other abnormalities. The image segmentation methods may be classified into several types: image-based, model-based and hybrid methods. Purely image-based methods perform segmentation based only on information available within the image. These include thresholding, region growing, morphological operations, active contours level sets, watershed, fuzzy connectedness, and graph cuts (Gcs).Image based methods perform well on high-quality images. However, the results are not as good when the image quality is inferior or boundary information is missing .One advantage of model based methods is that, even when some object information is missing, such gaps can be filled by drawing upon the prior information present in the model .In this paper a semi automated segmentation method is implemented for medical image segmentation. Tumor detection is one of the major applications of medical image segmentation .A tumor detection algorithm using fuzzy c means clustering is also implemented in this paper.