Detection of Bone Cancer in X-Ray Images

Abstract

A combined relation of engineering and medicine is termed as biomedical Engineering. Biomedical engineering has rooted its research in various imaging modalities such as Ultrasound, Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and other imaging techniques. The development of image processing based cancer detection from any imaging modality is one of the emerging research areas in the field of biomedical engineering. Bone cancer is one of the most dangerous cancer diseases in the world. Many researchers contributed more to bone cancer detection in CT and MRI images in their research. Detection of bone cancer can be done by analyzing the images of X-rays in the earlier stages.  Imaging with X-rays involves exposing a part of a body to a small dose of ionizing radiation to produce the internal structure of the body. Even though a lot of research is in the growing stage in bone cancer, still a lot of challenges exist in bone cancer. In this paper, a better feature extraction approach based on texture and gradient features for the identification of important distinct regions and the K Nearest Neighbor (KNN) classifier is used to classify the normal and cancer bone. When using the KNN classifier this methodology gave 98.3% classification accuracy.