Detection of Abnormalities in MRI Images using Texture Analysis

Abstract

Medical imaging technique is most commonly used to visualize the internal structure and function of the body. Magnetic Resonance Imaging provides much greater contrast between the different soft tissues of the body than computed tomography (CT) does, making it especially useful in neurological (brain), musculoskeletal, cardiovascular, and oncological (cancer) imaging. It is an image processing based method and this method may not provide complete diagnosis through the scanned images or their machines as performed by the medical agents. So, this method can even detect the smallest abnormality even in the earliest stage which the scan may or may not detect. Textures features of MR images have been provided. The analyses of both the normal and abnormal images are done. The ranges of both the types of images are calculated and then the comparison is performed between them. So, to determine the whether the abnormality is there or not in the image, its texture features are compared and the feature lying outside the range finally detects the abnormality in the biomedical image. In this thesis different MR scans of patients are taken having abnormality in their brain. Five cases are observed, on the bases of their comparison, the result is obtained at the end indicating the whether the presence of abnormality in the image.