Shape based image retrieval system for MRI spine

Image retrieval system (IRS) is a searching system that uses certain characteristics or context in an image. In the medical field, the IRS has been used to provide the needed correct images to the physicians while the diagnosis and treatment process is being conducted. In this paper, the research focus is on content-based IRS. In content-based IRS, two phases are discussed: feature extraction and selection, and the retrieval phase. The feature extraction technique is based on global shape descriptor (GSD), Hu moment invariant (Hu) and Fourier descriptor (FD) while the feature selection technique uses analysis of variance (ANOVA). The retrieval phase is implemented with the new feature vector formed and the performance is evaluated using four distance metrics namely Euclidean (E), Manhattan (M), Normalized Euclidean (NE) and Normalized Manhattan (NM). The experiment for CBIRS is performed on 100 MRI human spine images for each thoracic, lumbar and sacrum. The retrieval performances gave the best result for NM in retrieving the lumbar bones which the precision is up to 91.1%.