An Image Watermarking Algorithm for Medical Computerized Tomography Images

摘要

The increasing number of medical images and the need to share them among different treatment clinical centers lead to the widespread importance of medical image watermarking. However, it should maintain the quality of the image and extract the patient information from the encoded image properly. In this paper, an image watermarking algorithm for medical computerized tomography (CT) images is proposed, which consists of a combination of discrete wavelet transform (DWT) and singular value decomposition (SVD) methods. The proposed scheme is validated using CT images from different human organs that are collected from a clinical imaging center. To evaluate the invisibility of the watermarked image, the mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) metrics are computed. Also, the correlation coefficient (CRC) and the similarity measure (SIM) are utilized to assess the robustness of the proposed method for the extraction of the patient information from the watermarked image. The experimental results show that the proposed approach can achieve acceptable performance for encoding and decoding watermarking CT medical images.