A Self-Adaptive Image Segmentation-Based Dual Watermarking Technique for Medical Images

The smart healthcare system plays a more critical role than ever before. It is designed to share electronic patient records (EPR) to improve medical care and facilitate research. However, protecting the security of EPR data is still a significant challenge. This paper proposes a new method for safeguarding EPR data in such systems. The method is a self-adaptive image segmentation-based dual watermarking technique that embeds both EPR data and authentication information in the wavelet domain of selected region of non-interest (RONI) for enhanced security, imperceptibility, and robustness. The experiments are based on a large dataset of medical data, The Cancer Genome Atlas Lung Adenocarcinoma Collection (TCGA-LUAD). The results found that the method is effective for the smart healthcare system. Compared with existing techniques, the proposed approach is better regarding security, robustness, and capacity.