Classification of Knee Mri Images

Classification is very important part of digital image analysis. It is a computational procedure that sort images into groups according to their similarities. MRI is latest medical imaging technology. Magnetic Resonance Imaging used for Knee scans is very useful and effective technique to detect the knee joint defects. It is a non-invasive method to take picture of knee joint and the surrounding images. Classification of knee MR Images is done for the analysis purpose. In the preprocessing steps, segmentation is done using active contour without edges by chen and vese. Region containing cartilage thickness is separated out. During feature extraction part total 46 features have been extracted out of which 19 are DICOM image header features, 13 are haralick features and others are statistical moment features. Database file is prepared for 704 Knee MRI images and 46 attribute. In pre-processing 5 features has been removed. Database file is given as input for classification. As the result of classification FT algorithms classifies all instances correctly. Classification is done on the base of parameter ‘Slice Thickness’.