Medical Image Retrieval Based on Fractal Dimension

Content-based medical image retrieval becomes a hot research topic due to the rapid increase of image database. It is useful that a doctor consults analogical cases to diagnose for a patient. So it is very important for doctors to quickly and exactly search out the similar pathological images from large numbers of images in clinic. Fractal texture feature is introduced to medical images, according to experiments, it is discovered that the normal lung and several kinds of common lung diseases CT images have different fractal dimensions, which indicates that fractal dimensions of images can distinguish most lung diseases. Fractal feature is applied in medical images retrieval, and compared with general approaches, experiments show that high precision and recall of retrieval are achieved, and our method also can achieve a comparatively lower computation cost, and the retrieval time is short. The method is applied well and gives much better performance in medical images retrieval.