Content Based Medical Image Retrieval Using Lifting Scheme Based Discrete Wavelet Transform

Content based image retrieval technology has been proposed to benefit not only management of increasingly large image collection, but also to aid clinical care, biomedical research and education. In this paper, lifting scheme is proposed for content based retrieval method for diagnosis aid in medical field. Content-based image retrieval (CBIR) techniques could be valuable to radiologists in assessing medical images by identifying similar images in large archives that could assist with decision support. DWT is any wavelet transform for which the wavelets are discretely sampled. Although classical wavelet transform is effective in representing image feature and thus is suitable in CBIR, it still encounters problems especially in implementation, e.g. floating-point operation and decomposition speed, which may nicely be solved by lifting scheme. Lifting scheme is simplest and efficient algorithm to calculate wavelet transform. Lifting scheme used as feature in CBIR which has intriguing properties as faster implementation, low computation, easier to understand and can also be used for irregular sampling. Lifting scheme allows us to implement reversible integer wavelet transform. After extracting features using lifting scheme for both query image and database images for breast cancer images, Manhattan distance is used to calculate the similarity between the images for proper diagnosis which permits radiologist to identify whether the query image is malignant or normal tissue. Keywords—Content based image retrieval(CBIR),Discrete wavelets transform, lifting scheme, medical retrieval, image database.