Detection of Renal carcinoma in Ultrasound Images using HOG and SURF features

Abstract

Cancer can be defined as the abnormal growth of cells in any region of the human. Cancer cells possess a special property called metastasis that involves the movement of cells from one location to another location. Renal cancer is becoming predominant and there are different types. One among them is Renal cell carcinoma mainly occurs in the renal tubules. In this study, ultrasound images are considered for the detection of renal cell carcinoma. The images undergo pre-processing to remove speckle noises. The region of interest is defined using region growing technique. Later Feature descriptors like histogram of oriented gradient features and speeded up robust features are extracted from the segmented region for the analysis of carcinoma. Texture features are also derived along with these descriptors. These features are classified using Adaptive Support Vector Machine for the diagnosis of the renal cell carcinoma from normal images. With the performance of the classifier, it is defined that feature descriptors illustrate the region of carcinoma more effectively.