Automated Methods to Segment Kidneys and Detect Tumors Using CT Images

Abstract

Kidney tumors are of different types having different characteristics and also remain challenging in the field of biomedicine. It becomes very important to detect the tumor and classify it at the early stage so that appropriate treatment can be planned. The main objective of this research is to use the Computer-Aided Diagnosis (CAD) algorithms to help the early detection of kidney tumors. In this paper, tried to implement an automated segmentation methods of gray level CT images is used to provide information such as anatomical structure and identifying the Region of Interest (ROI) i.e. locate tumor, lesion and other in kidney.
A CT image has inhomogeneity, noise which affects the continuity and accuracy of the images segmentation. In order to obtain good accuracy; the noise must be removed from the input image. Those propose method is started with pre-processing of the kidney CT image to enhance its contrast and removing the undesired noise in order to make the image suitable for further processing. In our proposed work, we have proposed a hybrid filter as a combination of adaptive median and Gaussian HP filter for noise removal and image enhancement. The segmentation process is performed by using the Fuzzy C-Means (FCM) clustering and Watershed methods to detect and segment kidney CT images for the kidney region .The resulted segmented kidney CT images, and then used to extract the tumor region from kidney image.