Novel Shape Description for CBIR in Medical Application

Image Retrieval for Medical Applications (IRMA) has received a significant research interest over the past decade as a promising approach to address the data management challenges posed by the rapidly increasing volume of medical image data collections in use and also to aid clinical medicine, research, and education relying on visual content in the data. The research presented in this paper was aimed to improve the retrieval performance of an images retrieval system in medical applications based on shape features. In general, the work consists of two phases: (1) enrollment phase, which consist of feature extraction based on developed method to extract the shape features, (2) retrieving phase, which use the Euclidian distance measure. The conducted tests were carried on 350 medical images from four types (i.e., abdominal CT scan, MRI, ultrasonic, X-ray) and give good precision and recall rates (94,89).