Medical Image Retrieval Using Transforms

Abstract

The purpose of this study is to access the stability of transformation methods for medical image analysis. The reason for image retrieval is due to the increase in acquisition of images. Imaging has occupied a huge role in the management of patients, whether hospitalized or not. Depending upon the patient’s clinical problem, a variety of imaging modalities were available for use. In this article various distance methods were used and then they are compared for effective medical image retrieval. A transform based approach is followed for effective retrieval. This paper describes discrete Fourier transforms (DFT), discrete cosine transforms (DCT), discrete wavelet transforms(DWT), complex wavelet transforms (CWT) and rotated complex wavelet transform filter (RCWF) for medical image retrieval. From the final results it is very clear that each transforms performance defers and shows different results in retrieval of medical images. DWT shows the best results in terms of average retrieval results with 95% precision and 83% recall value, average searching time with 8 seconds, and less number of irrelevant images. These results indicate that these easily computable similarity distance measures have a wide variety of medical image retrieval applications.