WatMIF: Multimodal Medical Image Fusion-Based Watermarking for Telehealth Applications

Abstract

Over recent years, the volume of big data has drastically increased for medical applications. Such data are shared by cloud providers for storage and further processing. Medical images contain sensitive information, and these images are shared with healthcare workers, patients, and, in some scenarios, researchers for diagnostic and study purposes. However, the security of these images in the transfer process is extremely important, especially after the COVID-19 pandemic. This paper proposes a secure watermarking algorithm, termed WatMIF, based on multimodal medical image fusion. The proposed algorithm consists of three major parts: the encryption of the host media, the fusion of multimodal medical images, and the embedding and extraction of the fused mark. We encrypt the host media with a key-based encryption scheme. Then, a nonsubsampled contourlet transform (NSCT)-based fusion scheme is employed to fuse the magnetic resonance imaging (MRI) and computed tomography (CT) scan images to generate the fused mark image. Furthermore, the encrypted host media conceals the fused watermark using redundant discrete wavelet transform (RDWT) and randomised singular value decomposition (RSVD). Finally, denoising convolutional neural network (DnCNN) is used to improve the robustness of the WatMIF algorithm. The simulation experiments on two standard datasets were used to evaluate the algorithm in terms of invisibility, robustness, and security. When compared with the existing algorithms, the robustness is improved by 20.14%. Overall, the implementation of proposed watermarking for hiding fused marks and efficient encryption improved the identity verification, invisibility, robustness and security criteria in our WatMIF algorithm.

A robust and secured fusion based hybrid medical image watermarking approach using RDWT-DWT-MSVD with Hyperchaotic system-Fibonacci Q Matrix encryption

“…The watermarked image is finally encrypted with a hyperchaotic and DNA scheme to improve security. Singh et al [31] designed a MIW strategy for telemedicine applications. The cover image is encrypted using a key-based encryption scheme.…”

“…here f w (i, j ), f (i, j ), I w (i, j ), I (i, j ) are the watermarked image, original cover image, extracted mark, and original mark respectively. The encryption scheme's performance was tested by determining characteristics such as the Number of Changing Pixel Rate (NPCR), Unified Averaged Changed Intensity (UACI) [3], and Entropy (randomness) [31] given by ( 5), (7), and (8) respectively.…”

Robust and blind watermarking algorithm for chaotic system encryption based on discrete cosine transform-singular value decomposition

“…13: hand-crafted and deep learning. The deep learning technology represented by convolutional neural network has received numerous attentions due to its extraordinary performance in various problems of computer vision and pattern recognition 14 – 16 However, due to the data-driven nature, deep learning methods suffer from limitations in time and space costs.…”

“…The deep learning technology represented by convolutional neural network has received numerous attentions due to its extraordinary performance in various problems of computer vision and pattern recognition. [14][15][16] However, due to the data-driven nature, deep learning methods suffer from limitations in time and space costs. In contrast, as an important branch of hand-crafted image representation, moment invariants generally have a significant impact on the research of information security since a variety of attacks could affect the embedding and extraction process of watermarking.…”

Volumetric Model Genesis in Medical Domain for the Analysis of Multimodality 2-D/3-D Data Based on the Aggregation of Multilevel Features

“…For example, multimodal images such as CT and MRI images are being fused to create a single mark image that can be more suitable for diagnostic evaluation than individual images [3,4]. Recently, a variety of multimodal fusion-based algorithms are evolving for safe and secure telehealth applications [5].…”