Reversible data hiding in encrypted medical DICOM image

This paper proposes a novel reversible data hiding (RDH) scheme in encrypted domain for medical DICOM images. Although a lot of RDH schemes for encrypted images have been presented, however, most of them are unsuitable for medical DICOM images, as they do not utilize the features of the DICOM image format, and the recovery accuracy is low because medical images have large areas with the same pixel values. To avoid these weaknesses, our scheme segments the image and only embeds data into part of the encrypted image. The redundancy of pixel cells in DICOM images is exploited so that auxiliary data can be embedded into the image. The order of data extraction and image recovery, which can be optimized by the number of recovered blocks around the unrecovered block, is calculated to improve the recovery accuracy. In addition, to ensure the integrity of the DICOM image, the hash value of the minimum bounding rectangle of ROI and the feature bit matrix of the rest are calculated. If the image is tampered, the tampered area, especially ROI, can be accurately detected and located on the receiver side. Experimental results demonstrate the effectiveness of the proposed scheme.